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

Conflicts:
	drivers/net/wireless/orinoco/main.c

Documentation/RCU/rculist_nulls.txt

@@ -83,11 +83,12 @@ not detect it missed following items in original chain.
 obj = kmem_cache_alloc(...);
 lock_chain(); // typically a spin_lock()
 obj->key = key;
-atomic_inc(&obj->refcnt);
 /*
  * we need to make sure obj->key is updated before obj->next
+ * or obj->refcnt
  */
 smp_wmb();
+atomic_set(&obj->refcnt, 1);
 hlist_add_head_rcu(&obj->obj_node, list);
 unlock_chain(); // typically a spin_unlock()
 
@@ -159,6 +160,10 @@ out:
 obj = kmem_cache_alloc(cachep);
 lock_chain(); // typically a spin_lock()
 obj->key = key;
+/*
+ * changes to obj->key must be visible before refcnt one
+ */
+smp_wmb();
 atomic_set(&obj->refcnt, 1);
 /*
  * insert obj in RCU way (readers might be traversing chain)

MAINTAINERS

@@ -4089,6 +4089,7 @@ L:	netfilter@vger.kernel.org
 L:	coreteam@netfilter.org
 W:	http://www.netfilter.org/
 W:	http://www.iptables.org/
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6.git
 S:	Supported
 F:	include/linux/netfilter*
 F:	include/linux/netfilter/

drivers/net/8139too.c

@@ -908,6 +908,7 @@ static const struct net_device_ops rtl8139_netdev_ops = {
 	.ndo_open		= rtl8139_open,
 	.ndo_stop		= rtl8139_close,
 	.ndo_get_stats		= rtl8139_get_stats,
+	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= rtl8139_set_mac_address,
 	.ndo_start_xmit		= rtl8139_start_xmit,

drivers/net/arm/ixp4xx_eth.c

@@ -1142,7 +1142,9 @@ static const struct net_device_ops ixp4xx_netdev_ops = {
 	.ndo_start_xmit = eth_xmit,
 	.ndo_set_multicast_list = eth_set_mcast_list,
 	.ndo_do_ioctl = eth_ioctl,
-
+	.ndo_change_mtu = eth_change_mtu,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr = eth_validate_addr,
 };
 
 static int __devinit eth_init_one(struct platform_device *pdev)

drivers/net/atl1c/atl1c.h

@@ -188,14 +188,14 @@ struct atl1c_tpd_ext_desc {
 #define RRS_HDS_TYPE_DATA	2
 
 #define RRS_IS_NO_HDS_TYPE(flag) \
-	(((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK == 0)
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == 0)
 
 #define RRS_IS_HDS_HEAD(flag) \
-	(((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK == \
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == \
 			RRS_HDS_TYPE_HEAD)
 
 #define RRS_IS_HDS_DATA(flag) \
-	(((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK == \
+	((((flag) >> (RRS_HDS_TYPE_SHIFT)) & RRS_HDS_TYPE_MASK) == \
 			RRS_HDS_TYPE_DATA)
 
 /* rrs word 3 bit 0:31 */
@@ -245,7 +245,7 @@ struct atl1c_tpd_ext_desc {
 #define RRS_PACKET_TYPE_802_3  	1
 #define RRS_PACKET_TYPE_ETH	0
 #define RRS_PACKET_IS_ETH(word) \
-	(((word) >> RRS_PACKET_TYPE_SHIFT) & RRS_PACKET_TYPE_MASK == \
+	((((word) >> RRS_PACKET_TYPE_SHIFT) & RRS_PACKET_TYPE_MASK) == \
 			RRS_PACKET_TYPE_ETH)
 #define RRS_RXD_IS_VALID(word) \
 	((((word) >> RRS_RXD_UPDATED_SHIFT) & RRS_RXD_UPDATED_MASK) == 1)

drivers/net/atl1c/atl1c_main.c

@@ -1689,7 +1689,7 @@ static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter, u8 que,
 		if (likely(RRS_RXD_IS_VALID(rrs->word3))) {
 			rfd_num = (rrs->word0 >> RRS_RX_RFD_CNT_SHIFT) &
 				RRS_RX_RFD_CNT_MASK;
-			if (unlikely(rfd_num) != 1)
+			if (unlikely(rfd_num != 1))
 				/* TODO support mul rfd*/
 				if (netif_msg_rx_err(adapter))
 					dev_warn(&pdev->dev,

drivers/net/atlx/atl2.c

@@ -2071,7 +2071,7 @@ static int atl2_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE))
 		return -EOPNOTSUPP;
 
-	if (wol->wolopts & (WAKE_MCAST|WAKE_BCAST|WAKE_MCAST))
+	if (wol->wolopts & (WAKE_UCAST | WAKE_BCAST | WAKE_MCAST))
 		return -EOPNOTSUPP;
 
 	/* these settings will always override what we currently have */

drivers/net/bonding/bond_main.c

@@ -1459,8 +1459,16 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	 * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond
 	 */
 	if (bond->slave_cnt == 0) {
-		if (slave_dev->type != ARPHRD_ETHER)
-			bond_setup_by_slave(bond_dev, slave_dev);
+		if (bond_dev->type != slave_dev->type) {
+			dev_close(bond_dev);
+			pr_debug("%s: change device type from %d to %d\n",
+				bond_dev->name, bond_dev->type, slave_dev->type);
+			if (slave_dev->type != ARPHRD_ETHER)
+				bond_setup_by_slave(bond_dev, slave_dev);
+			else
+				ether_setup(bond_dev);
+			dev_open(bond_dev);
+		}
 	} else if (bond_dev->type != slave_dev->type) {
 		pr_err(DRV_NAME ": %s ether type (%d) is different "
 			"from other slaves (%d), can not enslave it.\n",

drivers/net/cs89x0.c

@@ -1524,6 +1524,7 @@ static void net_timeout(struct net_device *dev)
 static int net_send_packet(struct sk_buff *skb, struct net_device *dev)
 {
 	struct net_local *lp = netdev_priv(dev);
+	unsigned long flags;
 
 	if (net_debug > 3) {
 		printk("%s: sent %d byte packet of type %x\n",
@@ -1535,7 +1536,7 @@ static int net_send_packet(struct sk_buff *skb, struct net_device *dev)
                   ask the chip to start transmitting before the
                   whole packet has been completely uploaded. */
 
-	spin_lock_irq(&lp->lock);
+	spin_lock_irqsave(&lp->lock, flags);
 	netif_stop_queue(dev);
 
 	/* initiate a transmit sequence */
@@ -1549,13 +1550,13 @@ static int net_send_packet(struct sk_buff *skb, struct net_device *dev)
 		 * we're waiting for TxOk, so return 1 and requeue this packet.
 		 */
 
-		spin_unlock_irq(&lp->lock);
+		spin_unlock_irqrestore(&lp->lock, flags);
 		if (net_debug) printk("cs89x0: Tx buffer not free!\n");
 		return NETDEV_TX_BUSY;
 	}
 	/* Write the contents of the packet */
 	writewords(dev->base_addr, TX_FRAME_PORT,skb->data,(skb->len+1) >>1);
-	spin_unlock_irq(&lp->lock);
+	spin_unlock_irqrestore(&lp->lock, flags);
 	lp->stats.tx_bytes += skb->len;
 	dev->trans_start = jiffies;
 	dev_kfree_skb (skb);

drivers/net/e100.c

@@ -1897,6 +1897,9 @@ static int e100_rx_indicate(struct nic *nic, struct rx *rx,
 
 			if (ioread8(&nic->csr->scb.status) & rus_no_res)
 				nic->ru_running = RU_SUSPENDED;
+		pci_dma_sync_single_for_device(nic->pdev, rx->dma_addr,
+					       sizeof(struct rfd),
+					       PCI_DMA_BIDIRECTIONAL);
 		return -ENODATA;
 	}
 

drivers/net/ehea/ehea_main.c

@@ -3080,7 +3080,9 @@ static const struct net_device_ops ehea_netdev_ops = {
 	.ndo_poll_controller	= ehea_netpoll,
 #endif
 	.ndo_get_stats		= ehea_get_stats,
+	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_set_mac_address	= ehea_set_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_multicast_list	= ehea_set_multicast_list,
 	.ndo_change_mtu		= ehea_change_mtu,
 	.ndo_vlan_rx_register	= ehea_vlan_rx_register,

drivers/net/fec.c

@@ -1642,6 +1642,7 @@ static const struct net_device_ops fec_netdev_ops = {
 	.ndo_stop		= fec_enet_close,
 	.ndo_start_xmit		= fec_enet_start_xmit,
 	.ndo_set_multicast_list = set_multicast_list,
+	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= fec_timeout,
 	.ndo_set_mac_address	= fec_set_mac_address,

drivers/net/gianfar.c

@@ -156,6 +156,8 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_tx_timeout = gfar_timeout,
 	.ndo_do_ioctl = gfar_ioctl,
 	.ndo_vlan_rx_register = gfar_vlan_rx_register,
+	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_validate_addr = eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = gfar_netpoll,
 #endif

drivers/net/igb/igb_main.c

@@ -127,14 +127,48 @@ static void igb_restore_vlan(struct igb_adapter *);
 static void igb_ping_all_vfs(struct igb_adapter *);
 static void igb_msg_task(struct igb_adapter *);
 static int igb_rcv_msg_from_vf(struct igb_adapter *, u32);
-static inline void igb_set_rah_pool(struct e1000_hw *, int , int);
 static void igb_set_mc_list_pools(struct igb_adapter *, int, u16);
 static void igb_vmm_control(struct igb_adapter *);
-static inline void igb_set_vmolr(struct e1000_hw *, int);
-static inline int igb_set_vf_rlpml(struct igb_adapter *, int, int);
 static int igb_set_vf_mac(struct igb_adapter *adapter, int, unsigned char *);
 static void igb_restore_vf_multicasts(struct igb_adapter *adapter);
 
+static inline void igb_set_vmolr(struct e1000_hw *hw, int vfn)
+{
+	u32 reg_data;
+
+	reg_data = rd32(E1000_VMOLR(vfn));
+	reg_data |= E1000_VMOLR_BAM |	 /* Accept broadcast */
+	            E1000_VMOLR_ROPE |   /* Accept packets matched in UTA */
+	            E1000_VMOLR_ROMPE |  /* Accept packets matched in MTA */
+	            E1000_VMOLR_AUPE |   /* Accept untagged packets */
+	            E1000_VMOLR_STRVLAN; /* Strip vlan tags */
+	wr32(E1000_VMOLR(vfn), reg_data);
+}
+
+static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size,
+                                 int vfn)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	u32 vmolr;
+
+	vmolr = rd32(E1000_VMOLR(vfn));
+	vmolr &= ~E1000_VMOLR_RLPML_MASK;
+	vmolr |= size | E1000_VMOLR_LPE;
+	wr32(E1000_VMOLR(vfn), vmolr);
+
+	return 0;
+}
+
+static inline void igb_set_rah_pool(struct e1000_hw *hw, int pool, int entry)
+{
+	u32 reg_data;
+
+	reg_data = rd32(E1000_RAH(entry));
+	reg_data &= ~E1000_RAH_POOL_MASK;
+	reg_data |= E1000_RAH_POOL_1 << pool;;
+	wr32(E1000_RAH(entry), reg_data);
+}
+
 #ifdef CONFIG_PM
 static int igb_suspend(struct pci_dev *, pm_message_t);
 static int igb_resume(struct pci_dev *);
@@ -5418,43 +5452,6 @@ static void igb_io_resume(struct pci_dev *pdev)
 	igb_get_hw_control(adapter);
 }
 
-static inline void igb_set_vmolr(struct e1000_hw *hw, int vfn)
-{
-	u32 reg_data;
-
-	reg_data = rd32(E1000_VMOLR(vfn));
-	reg_data |= E1000_VMOLR_BAM |	 /* Accept broadcast */
-	            E1000_VMOLR_ROPE |   /* Accept packets matched in UTA */
-	            E1000_VMOLR_ROMPE |  /* Accept packets matched in MTA */
-	            E1000_VMOLR_AUPE |   /* Accept untagged packets */
-	            E1000_VMOLR_STRVLAN; /* Strip vlan tags */
-	wr32(E1000_VMOLR(vfn), reg_data);
-}
-
-static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size,
-                                 int vfn)
-{
-	struct e1000_hw *hw = &adapter->hw;
-	u32 vmolr;
-
-	vmolr = rd32(E1000_VMOLR(vfn));
-	vmolr &= ~E1000_VMOLR_RLPML_MASK;
-	vmolr |= size | E1000_VMOLR_LPE;
-	wr32(E1000_VMOLR(vfn), vmolr);
-
-	return 0;
-}
-
-static inline void igb_set_rah_pool(struct e1000_hw *hw, int pool, int entry)
-{
-	u32 reg_data;
-
-	reg_data = rd32(E1000_RAH(entry));
-	reg_data &= ~E1000_RAH_POOL_MASK;
-	reg_data |= E1000_RAH_POOL_1 << pool;;
-	wr32(E1000_RAH(entry), reg_data);
-}
-
 static void igb_set_mc_list_pools(struct igb_adapter *adapter,
 				  int entry_count, u16 total_rar_filters)
 {

drivers/net/isa-skeleton.c

@@ -430,7 +430,8 @@ static int net_send_packet(struct sk_buff *skb, struct net_device *dev)
 	 * hardware interrupt handler.  Queue flow control is
 	 * thus managed under this lock as well.
 	 */
-	spin_lock_irq(&np->lock);
+	unsigned long flags;
+	spin_lock_irqsave(&np->lock, flags);
 
 	add_to_tx_ring(np, skb, length);
 	dev->trans_start = jiffies;
@@ -446,7 +447,7 @@ static int net_send_packet(struct sk_buff *skb, struct net_device *dev)
 	 * is when the transmit statistics are updated.
 	 */
 
-	spin_unlock_irq(&np->lock);
+	spin_unlock_irqrestore(&np->lock, flags);
 #else
 	/* This is the case for older hardware which takes
 	 * a single transmit buffer at a time, and it is

drivers/net/ixgbe/ixgbe_dcb_nl.c

@@ -106,8 +106,6 @@ static u8 ixgbe_dcbnl_get_state(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	DPRINTK(DRV, INFO, "Get DCB Admin Mode.\n");
-
 	return !!(adapter->flags & IXGBE_FLAG_DCB_ENABLED);
 }
 
@@ -116,8 +114,6 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
 	u8 err = 0;
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	DPRINTK(DRV, INFO, "Set DCB Admin Mode.\n");
-
 	if (state > 0) {
 		/* Turn on DCB */
 		if (adapter->flags & IXGBE_FLAG_DCB_ENABLED)
@@ -175,6 +171,8 @@ static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev,
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	int i, j;
 
+	memset(perm_addr, 0xff, MAX_ADDR_LEN);
+
 	for (i = 0; i < netdev->addr_len; i++)
 		perm_addr[i] = adapter->hw.mac.perm_addr[i];
 

drivers/net/phy/phy_device.c

@@ -134,8 +134,10 @@ int phy_scan_fixups(struct phy_device *phydev)
 
 			err = fixup->run(phydev);
 
-			if (err < 0)
+			if (err < 0) {
+				mutex_unlock(&phy_fixup_lock);
 				return err;
+			}
 		}
 	}
 	mutex_unlock(&phy_fixup_lock);

drivers/net/plip.c

@@ -270,6 +270,9 @@ static const struct net_device_ops plip_netdev_ops = {
 	.ndo_stop		 = plip_close,
 	.ndo_start_xmit		 = plip_tx_packet,
 	.ndo_do_ioctl		 = plip_ioctl,
+	.ndo_change_mtu		 = eth_change_mtu,
+	.ndo_set_mac_address	 = eth_mac_addr,
+	.ndo_validate_addr	 = eth_validate_addr,
 };
 
 /* Entry point of PLIP driver.

drivers/net/ps3_gelic_net.c

@@ -1411,6 +1411,7 @@ static const struct net_device_ops gelic_netdevice_ops = {
 	.ndo_set_multicast_list = gelic_net_set_multi,
 	.ndo_change_mtu = gelic_net_change_mtu,
 	.ndo_tx_timeout = gelic_net_tx_timeout,
+	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = gelic_net_poll_controller,

drivers/net/ps3_gelic_wireless.c

@@ -2707,6 +2707,7 @@ static const struct net_device_ops gelic_wl_netdevice_ops = {
 	.ndo_set_multicast_list = gelic_net_set_multi,
 	.ndo_change_mtu = gelic_net_change_mtu,
 	.ndo_tx_timeout = gelic_net_tx_timeout,
+	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = gelic_net_poll_controller,

drivers/net/sky2.c

@@ -1151,14 +1151,7 @@ static void sky2_rx_stop(struct sky2_port *sky2)
 
 	/* reset the Rx prefetch unit */
 	sky2_write32(hw, Y2_QADDR(rxq, PREF_UNIT_CTRL), PREF_UNIT_RST_SET);
-
-	/* Reset the RAM Buffer receive queue */
-	sky2_write8(hw, RB_ADDR(rxq, RB_CTRL), RB_RST_SET);
-
-	/* Reset Rx MAC FIFO */
-	sky2_write8(hw, SK_REG(sky2->port, RX_GMF_CTRL_T), GMF_RST_SET);
-
-	sky2_read8(hw, B0_CTST);
+	mmiowb();
 }
 
 /* Clean out receive buffer area, assumes receiver hardware stopped */

drivers/net/smc91x.c

@@ -1774,6 +1774,7 @@ static const struct net_device_ops smc_netdev_ops = {
 	.ndo_start_xmit		= smc_hard_start_xmit,
 	.ndo_tx_timeout		= smc_timeout,
 	.ndo_set_multicast_list	= smc_set_multicast_list,
+	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER

drivers/net/smsc911x.c

@@ -1779,6 +1779,7 @@ static const struct net_device_ops smsc911x_netdev_ops = {
 	.ndo_get_stats		= smsc911x_get_stats,
 	.ndo_set_multicast_list	= smsc911x_set_multicast_list,
 	.ndo_do_ioctl		= smsc911x_do_ioctl,
+	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address 	= smsc911x_set_mac_address,
 #ifdef CONFIG_NET_POLL_CONTROLLER

drivers/net/sunvnet.c

@@ -1016,7 +1016,9 @@ static const struct net_device_ops vnet_ops = {
 	.ndo_open		= vnet_open,
 	.ndo_stop		= vnet_close,
 	.ndo_set_multicast_list	= vnet_set_rx_mode,
+	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_set_mac_address	= vnet_set_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= vnet_tx_timeout,
 	.ndo_change_mtu		= vnet_change_mtu,
 	.ndo_start_xmit		= vnet_start_xmit,

drivers/net/usb/cdc_eem.c

@@ -311,7 +311,7 @@ static int eem_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 			 *	bmCRC = 0	: CRC = 0xDEADBEEF
 			 */
 			if (header & BIT(14))
-				crc2 = ~crc32_le(~0, skb2->data, len);
+				crc2 = ~crc32_le(~0, skb2->data, skb2->len);
 			else
 				crc2 = 0xdeadbeef;
 

drivers/net/usb/kaweth.c

@@ -999,6 +999,9 @@ static const struct net_device_ops kaweth_netdev_ops = {
 	.ndo_tx_timeout =		kaweth_tx_timeout,
 	.ndo_set_multicast_list =	kaweth_set_rx_mode,
 	.ndo_get_stats =		kaweth_netdev_stats,
+	.ndo_change_mtu =		eth_change_mtu,
+	.ndo_set_mac_address =		eth_mac_addr,
+	.ndo_validate_addr =		eth_validate_addr,
 };
 
 static int kaweth_probe(

drivers/net/usb/pegasus.c

@@ -1493,6 +1493,9 @@ static const struct net_device_ops pegasus_netdev_ops = {
 	.ndo_set_multicast_list =	pegasus_set_multicast,
 	.ndo_get_stats =		pegasus_netdev_stats,
 	.ndo_tx_timeout =		pegasus_tx_timeout,
+	.ndo_change_mtu =		eth_change_mtu,
+	.ndo_set_mac_address =		eth_mac_addr,
+	.ndo_validate_addr =		eth_validate_addr,
 };
 
 static struct usb_driver pegasus_driver = {

drivers/net/via-rhine.c

@@ -621,6 +621,7 @@ static const struct net_device_ops rhine_netdev_ops = {
 	.ndo_start_xmit		 = rhine_start_tx,
 	.ndo_get_stats		 = rhine_get_stats,
 	.ndo_set_multicast_list	 = rhine_set_rx_mode,
+	.ndo_change_mtu		 = eth_change_mtu,
 	.ndo_validate_addr	 = eth_validate_addr,
 	.ndo_set_mac_address 	 = eth_mac_addr,
 	.ndo_do_ioctl		 = netdev_ioctl,

drivers/net/wireless/orinoco/main.c

@@ -2072,6 +2072,8 @@ static const struct net_device_ops orinoco_netdev_ops = {
 	.ndo_start_xmit		= orinoco_xmit,
 	.ndo_set_multicast_list	= orinoco_set_multicast_list,
 	.ndo_change_mtu		= orinoco_change_mtu,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_tx_timeout		= orinoco_tx_timeout,
 	.ndo_get_stats		= orinoco_get_stats,
 };

include/linux/skbuff.h

@@ -1342,12 +1342,12 @@ static inline int skb_network_offset(const struct sk_buff *skb)
  * shifting the start of the packet by 2 bytes. Drivers should do this
  * with:
  *
- * skb_reserve(NET_IP_ALIGN);
+ * skb_reserve(skb, NET_IP_ALIGN);
  *
  * The downside to this alignment of the IP header is that the DMA is now
  * unaligned. On some architectures the cost of an unaligned DMA is high
  * and this cost outweighs the gains made by aligning the IP header.
- * 
+ *
  * Since this trade off varies between architectures, we allow NET_IP_ALIGN
  * to be overridden.
  */

include/net/sock.h

@@ -104,15 +104,15 @@ struct net;
 
 /**
  *	struct sock_common - minimal network layer representation of sockets
+ *	@skc_node: main hash linkage for various protocol lookup tables
+ *	@skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol
+ *	@skc_refcnt: reference count
+ *	@skc_hash: hash value used with various protocol lookup tables
  *	@skc_family: network address family
  *	@skc_state: Connection state
  *	@skc_reuse: %SO_REUSEADDR setting
  *	@skc_bound_dev_if: bound device index if != 0
- *	@skc_node: main hash linkage for various protocol lookup tables
- *	@skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol
  *	@skc_bind_node: bind hash linkage for various protocol lookup tables
- *	@skc_refcnt: reference count
- *	@skc_hash: hash value used with various protocol lookup tables
  *	@skc_prot: protocol handlers inside a network family
  *	@skc_net: reference to the network namespace of this socket
  *
@@ -120,17 +120,21 @@ struct net;
  *	for struct sock and struct inet_timewait_sock.
  */
 struct sock_common {
-	unsigned short		skc_family;
-	volatile unsigned char	skc_state;
-	unsigned char		skc_reuse;
-	int			skc_bound_dev_if;
+	/*
+	 * first fields are not copied in sock_copy()
+	 */
 	union {
 		struct hlist_node	skc_node;
 		struct hlist_nulls_node skc_nulls_node;
 	};
-	struct hlist_node	skc_bind_node;
 	atomic_t		skc_refcnt;
+
 	unsigned int		skc_hash;
+	unsigned short		skc_family;
+	volatile unsigned char	skc_state;
+	unsigned char		skc_reuse;
+	int			skc_bound_dev_if;
+	struct hlist_node	skc_bind_node;
 	struct proto		*skc_prot;
 #ifdef CONFIG_NET_NS
 	struct net	 	*skc_net;
@@ -208,15 +212,17 @@ struct sock {
 	 * don't add nothing before this first member (__sk_common) --acme
 	 */
 	struct sock_common	__sk_common;
+#define sk_node			__sk_common.skc_node
+#define sk_nulls_node		__sk_common.skc_nulls_node
+#define sk_refcnt		__sk_common.skc_refcnt
+
+#define sk_copy_start		__sk_common.skc_hash
+#define sk_hash			__sk_common.skc_hash
 #define sk_family		__sk_common.skc_family
 #define sk_state		__sk_common.skc_state
 #define sk_reuse		__sk_common.skc_reuse
 #define sk_bound_dev_if		__sk_common.skc_bound_dev_if
-#define sk_node			__sk_common.skc_node
-#define sk_nulls_node		__sk_common.skc_nulls_node
 #define sk_bind_node		__sk_common.skc_bind_node
-#define sk_refcnt		__sk_common.skc_refcnt
-#define sk_hash			__sk_common.skc_hash
 #define sk_prot			__sk_common.skc_prot
 #define sk_net			__sk_common.skc_net
 	kmemcheck_bitfield_begin(flags);

net/can/bcm.c

@@ -75,6 +75,7 @@ static __initdata const char banner[] = KERN_INFO
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
+MODULE_ALIAS("can-proto-2");
 
 /* easy access to can_frame payload */
 static inline u64 GET_U64(const struct can_frame *cp)
@@ -1469,6 +1470,9 @@ static int bcm_release(struct socket *sock)
 		bo->ifindex = 0;
 	}
 
+	sock_orphan(sk);
+	sock->sk = NULL;
+
 	release_sock(sk);
 	sock_put(sk);
 

net/can/raw.c

@@ -62,6 +62,7 @@ static __initdata const char banner[] =
 MODULE_DESCRIPTION("PF_CAN raw protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
+MODULE_ALIAS("can-proto-1");
 
 #define MASK_ALL 0
 
@@ -306,6 +307,9 @@ static int raw_release(struct socket *sock)
 	ro->bound   = 0;
 	ro->count   = 0;
 
+	sock_orphan(sk);
+	sock->sk = NULL;
+
 	release_sock(sk);
 	sock_put(sk);
 

net/core/sock.c

@@ -919,13 +919,19 @@ static inline void sock_lock_init(struct sock *sk)
 			af_family_keys + sk->sk_family);
 }
 
+/*
+ * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet,
+ * even temporarly, because of RCU lookups. sk_node should also be left as is.
+ */
 static void sock_copy(struct sock *nsk, const struct sock *osk)
 {
 #ifdef CONFIG_SECURITY_NETWORK
 	void *sptr = nsk->sk_security;
 #endif
-
-	memcpy(nsk, osk, osk->sk_prot->obj_size);
+	BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) !=
+		     sizeof(osk->sk_node) + sizeof(osk->sk_refcnt));
+	memcpy(&nsk->sk_copy_start, &osk->sk_copy_start,
+	       osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start));
 #ifdef CONFIG_SECURITY_NETWORK
 	nsk->sk_security = sptr;
 	security_sk_clone(osk, nsk);
@@ -939,8 +945,23 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
 	struct kmem_cache *slab;
 
 	slab = prot->slab;
-	if (slab != NULL)
-		sk = kmem_cache_alloc(slab, priority);
+	if (slab != NULL) {
+		sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
+		if (!sk)
+			return sk;
+		if (priority & __GFP_ZERO) {
+			/*
+			 * caches using SLAB_DESTROY_BY_RCU should let
+			 * sk_node.next un-modified. Special care is taken
+			 * when initializing object to zero.
+			 */
+			if (offsetof(struct sock, sk_node.next) != 0)
+				memset(sk, 0, offsetof(struct sock, sk_node.next));
+			memset(&sk->sk_node.pprev, 0,
+			       prot->obj_size - offsetof(struct sock,
+							 sk_node.pprev));
+		}
+	}
 	else
 		sk = kmalloc(prot->obj_size, priority);
 
@@ -1125,6 +1146,11 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 
 		newsk->sk_err	   = 0;
 		newsk->sk_priority = 0;
+		/*
+		 * Before updating sk_refcnt, we must commit prior changes to memory
+		 * (Documentation/RCU/rculist_nulls.txt for details)
+		 */
+		smp_wmb();
 		atomic_set(&newsk->sk_refcnt, 2);
 
 		/*
@@ -1840,6 +1866,11 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	sk->sk_stamp = ktime_set(-1L, 0);
 
+	/*
+	 * Before updating sk_refcnt, we must commit prior changes to memory
+	 * (Documentation/RCU/rculist_nulls.txt for details)
+	 */
+	smp_wmb();
 	atomic_set(&sk->sk_refcnt, 1);
 	atomic_set(&sk->sk_wmem_alloc, 1);
 	atomic_set(&sk->sk_drops, 0);

net/ipv4/ip_gre.c

@@ -735,10 +735,10 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	tos = tiph->tos;
-	if (tos&1) {
+	if (tos == 1) {
+		tos = 0;
 		if (skb->protocol == htons(ETH_P_IP))
 			tos = old_iph->tos;
-		tos &= ~1;
 	}
 
 	{

net/ipv4/ip_output.c

@@ -1243,7 +1243,6 @@ int ip_push_pending_frames(struct sock *sk)
 		skb->len += tmp_skb->len;
 		skb->data_len += tmp_skb->len;
 		skb->truesize += tmp_skb->truesize;
-		__sock_put(tmp_skb->sk);
 		tmp_skb->destructor = NULL;
 		tmp_skb->sk = NULL;
 	}

net/ipv6/ip6_output.c

@@ -1474,7 +1474,6 @@ int ip6_push_pending_frames(struct sock *sk)
 		skb->len += tmp_skb->len;
 		skb->data_len += tmp_skb->len;
 		skb->truesize += tmp_skb->truesize;
-		__sock_put(tmp_skb->sk);
 		tmp_skb->destructor = NULL;
 		tmp_skb->sk = NULL;
 	}

net/ipv6/sit.c

@@ -1018,6 +1018,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->hard_header_len 	= LL_MAX_HEADER + sizeof(struct iphdr);
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr);
 	dev->flags		= IFF_NOARP;
+	dev->priv_flags	       &= ~IFF_XMIT_DST_RELEASE;
 	dev->iflink		= 0;
 	dev->addr_len		= 4;
 	dev->features		|= NETIF_F_NETNS_LOCAL;

net/netfilter/nf_conntrack_core.c

@@ -561,23 +561,38 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
 		}
 	}
 
-	ct = kmem_cache_zalloc(nf_conntrack_cachep, gfp);
+	/*
+	 * Do not use kmem_cache_zalloc(), as this cache uses
+	 * SLAB_DESTROY_BY_RCU.
+	 */
+	ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
 	if (ct == NULL) {
 		pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n");
 		atomic_dec(&net->ct.count);
 		return ERR_PTR(-ENOMEM);
 	}
-
+	/*
+	 * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next
+	 * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged.
+	 */
+	memset(&ct->tuplehash[IP_CT_DIR_MAX], 0,
+	       sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
 	spin_lock_init(&ct->lock);
-	atomic_set(&ct->ct_general.use, 1);
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
+	ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
 	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
+	ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL;
 	/* Don't set timer yet: wait for confirmation */
 	setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
 #ifdef CONFIG_NET_NS
 	ct->ct_net = net;
 #endif
 
+	/*
+	 * changes to lookup keys must be done before setting refcnt to 1
+	 */
+	smp_wmb();
+	atomic_set(&ct->ct_general.use, 1);
 	return ct;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_alloc);

net/netfilter/xt_osf.c

@@ -330,7 +330,8 @@ static bool xt_osf_match_packet(const struct sk_buff *skb,
 			fcount++;
 
 			if (info->flags & XT_OSF_LOG)
-				nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL,
+				nf_log_packet(p->family, p->hooknum, skb,
+					p->in, p->out, NULL,
 					"%s [%s:%s] : %pi4:%d -> %pi4:%d hops=%d\n",
 					f->genre, f->version, f->subtype,
 					&ip->saddr, ntohs(tcp->source),
@@ -345,7 +346,7 @@ static bool xt_osf_match_packet(const struct sk_buff *skb,
 	rcu_read_unlock();
 
 	if (!fcount && (info->flags & XT_OSF_LOG))
-		nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL,
+		nf_log_packet(p->family, p->hooknum, skb, p->in, p->out, NULL,
 			"Remote OS is not known: %pi4:%u -> %pi4:%u\n",
 				&ip->saddr, ntohs(tcp->source),
 				&ip->daddr, ntohs(tcp->dest));