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

Pull networking fixes from David S. Miller:

 1) Since we do RCU lookups on ipv4 FIB entries, we have to test if the
    entry is dead before returning it to our caller.

 2) openvswitch locking and packet validation fixes from Ansis Atteka,
    Jesse Gross, and Pravin B Shelar.

 3) Fix PM resume locking in IGB driver, from Benjamin Poirier.

 4) Fix VLAN header handling in vhost-net and macvtap, from Basil Gor.

 5) Revert a bogus network namespace isolation change that was causing
    regressions on S390 networking devices.

 6) If bonding decides to process and handle a LACPDU frame, we
    shouldn't bump the rx_dropped counter.  From Jiri Bohac.

 7) Fix mis-calculation of available TX space in r8169 driver when doing
    TSO, which can lead to crashes and/or hung device.  From Julien
    Ducourthial.

 8) SCTP does not validate cached routes properly in all cases, from
    Nicolas Dichtel.

 9) Link status interrupt needs to be handled in ks8851 driver, from
    Stephen Boyd.

10) Use capable(), not cap_raised(), in connector/userns netlink code.
    From Eric W. Biederman via Andrew Morton.

11) Fix pktgen OOPS on module unload, from Eric Dumazet.

12) iwlwifi under-estimates SKB truesizes, also from Eric Dumazet.

13) Cure division by zero in SFC driver, from Ben Hutchings.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (26 commits)
  ks8851: Update link status during link change interrupt
  macvtap: restore vlan header on user read
  vhost-net: fix handle_rx buffer size
  bonding: don't increase rx_dropped after processing LACPDUs
  connector/userns: replace netlink uses of cap_raised() with capable()
  sctp: check cached dst before using it
  pktgen: fix crash at module unload
  Revert "net: maintain namespace isolation between vlan and real device"
  ehea: fix losing of NEQ events when one event occurred early
  igb: fix rtnl race in PM resume path
  ipv4: Do not use dead fib_info entries.
  r8169: fix unsigned int wraparound with TSO
  sfc: Fix division by zero when using one RX channel and no SR-IOV
  openvswitch: Validation of IPv6 set port action uses IPv4 header
  net: compare_ether_addr[_64bits]() has no ordering
  cdc_ether: Ignore bogus union descriptor for RNDIS devices
  bnx2x: bug fix when loading after SAN boot
  e1000: Silence sparse warnings by correcting type
  igb, ixgbe: netdev_tx_reset_queue incorrectly called from tx init path
  openvswitch: Release rtnl_lock if ovs_vport_cmd_build_info() failed.
  ...

Author: torvalds

drivers/block/drbd/drbd_nl.c

@@ -2297,7 +2297,7 @@ static void drbd_connector_callback(struct cn_msg *req, struct netlink_skb_parms
 		return;
 	}
 
-	if (!cap_raised(current_cap(), CAP_SYS_ADMIN)) {
+	if (!capable(CAP_SYS_ADMIN)) {
 		retcode = ERR_PERM;
 		goto fail;
 	}

drivers/md/dm-log-userspace-transfer.c

@@ -134,7 +134,7 @@ static void cn_ulog_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp)
 {
 	struct dm_ulog_request *tfr = (struct dm_ulog_request *)(msg + 1);
 
-	if (!cap_raised(current_cap(), CAP_SYS_ADMIN))
+	if (!capable(CAP_SYS_ADMIN))
 		return;
 
 	spin_lock(&receiving_list_lock);

drivers/net/bonding/bond_3ad.c

@@ -2173,9 +2173,10 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
  * received frames (loopback). Since only the payload is given to this
  * function, it check for loopback.
  */
-static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u16 length)
+static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u16 length)
 {
 	struct port *port;
+	int ret = RX_HANDLER_ANOTHER;
 
 	if (length >= sizeof(struct lacpdu)) {
 
@@ -2184,11 +2185,12 @@ static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u
 		if (!port->slave) {
 			pr_warning("%s: Warning: port of slave %s is uninitialized\n",
 				   slave->dev->name, slave->dev->master->name);
-			return;
+			return ret;
 		}
 
 		switch (lacpdu->subtype) {
 		case AD_TYPE_LACPDU:
+			ret = RX_HANDLER_CONSUMED;
 			pr_debug("Received LACPDU on port %d\n",
 				 port->actor_port_number);
 			/* Protect against concurrent state machines */
@@ -2198,6 +2200,7 @@ static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u
 			break;
 
 		case AD_TYPE_MARKER:
+			ret = RX_HANDLER_CONSUMED;
 			// No need to convert fields to Little Endian since we don't use the marker's fields.
 
 			switch (((struct bond_marker *)lacpdu)->tlv_type) {
@@ -2219,6 +2222,7 @@ static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u
 			}
 		}
 	}
+	return ret;
 }
 
 /**
@@ -2456,18 +2460,20 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-void bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond,
+int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond,
 			  struct slave *slave)
 {
+	int ret = RX_HANDLER_ANOTHER;
 	if (skb->protocol != PKT_TYPE_LACPDU)
-		return;
+		return ret;
 
 	if (!pskb_may_pull(skb, sizeof(struct lacpdu)))
-		return;
+		return ret;
 
 	read_lock(&bond->lock);
-	bond_3ad_rx_indication((struct lacpdu *) skb->data, slave, skb->len);
+	ret = bond_3ad_rx_indication((struct lacpdu *) skb->data, slave, skb->len);
 	read_unlock(&bond->lock);
+	return ret;
 }
 
 /*

drivers/net/bonding/bond_3ad.h

@@ -274,7 +274,7 @@ void bond_3ad_adapter_duplex_changed(struct slave *slave);
 void bond_3ad_handle_link_change(struct slave *slave, char link);
 int  bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info);
 int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev);
-void bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond,
+int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct bonding *bond,
 			  struct slave *slave);
 int bond_3ad_set_carrier(struct bonding *bond);
 void bond_3ad_update_lacp_rate(struct bonding *bond);

drivers/net/bonding/bond_main.c

@@ -1444,8 +1444,9 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 	struct sk_buff *skb = *pskb;
 	struct slave *slave;
 	struct bonding *bond;
-	void (*recv_probe)(struct sk_buff *, struct bonding *,
+	int (*recv_probe)(struct sk_buff *, struct bonding *,
 				struct slave *);
+	int ret = RX_HANDLER_ANOTHER;
 
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
@@ -1464,8 +1465,12 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
 
 		if (likely(nskb)) {
-			recv_probe(nskb, bond, slave);
+			ret = recv_probe(nskb, bond, slave);
 			dev_kfree_skb(nskb);
+			if (ret == RX_HANDLER_CONSUMED) {
+				consume_skb(skb);
+				return ret;
+			}
 		}
 	}
 
@@ -1487,7 +1492,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 		memcpy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, ETH_ALEN);
 	}
 
-	return RX_HANDLER_ANOTHER;
+	return ret;
 }
 
 /* enslave device <slave> to bond device <master> */
@@ -2723,15 +2728,15 @@ static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32
 	}
 }
 
-static void bond_arp_rcv(struct sk_buff *skb, struct bonding *bond,
+static int bond_arp_rcv(struct sk_buff *skb, struct bonding *bond,
 			 struct slave *slave)
 {
 	struct arphdr *arp;
 	unsigned char *arp_ptr;
 	__be32 sip, tip;
 
 	if (skb->protocol != __cpu_to_be16(ETH_P_ARP))
-		return;
+		return RX_HANDLER_ANOTHER;
 
 	read_lock(&bond->lock);
 
@@ -2776,6 +2781,7 @@ static void bond_arp_rcv(struct sk_buff *skb, struct bonding *bond,
 
 out_unlock:
 	read_unlock(&bond->lock);
+	return RX_HANDLER_ANOTHER;
 }
 
 /*

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

@@ -9122,13 +9122,34 @@ static int __devinit bnx2x_prev_unload_common(struct bnx2x *bp)
 	return bnx2x_prev_mcp_done(bp);
 }
 
+/* previous driver DMAE transaction may have occurred when pre-boot stage ended
+ * and boot began, or when kdump kernel was loaded. Either case would invalidate
+ * the addresses of the transaction, resulting in was-error bit set in the pci
+ * causing all hw-to-host pcie transactions to timeout. If this happened we want
+ * to clear the interrupt which detected this from the pglueb and the was done
+ * bit
+ */
+static void __devinit bnx2x_prev_interrupted_dmae(struct bnx2x *bp)
+{
+	u32 val = REG_RD(bp, PGLUE_B_REG_PGLUE_B_INT_STS);
+	if (val & PGLUE_B_PGLUE_B_INT_STS_REG_WAS_ERROR_ATTN) {
+		BNX2X_ERR("was error bit was found to be set in pglueb upon startup. Clearing");
+		REG_WR(bp, PGLUE_B_REG_WAS_ERROR_PF_7_0_CLR, 1 << BP_FUNC(bp));
+	}
+}
+
 static int __devinit bnx2x_prev_unload(struct bnx2x *bp)
 {
 	int time_counter = 10;
 	u32 rc, fw, hw_lock_reg, hw_lock_val;
 	BNX2X_DEV_INFO("Entering Previous Unload Flow\n");
 
-       /* Release previously held locks */
+	/* clear hw from errors which may have resulted from an interrupted
+	 * dmae transaction.
+	 */
+	bnx2x_prev_interrupted_dmae(bp);
+
+	/* Release previously held locks */
 	hw_lock_reg = (BP_FUNC(bp) <= 5) ?
 		      (MISC_REG_DRIVER_CONTROL_1 + BP_FUNC(bp) * 8) :
 		      (MISC_REG_DRIVER_CONTROL_7 + (BP_FUNC(bp) - 6) * 8);

drivers/net/ethernet/ibm/ehea/ehea_main.c

@@ -3335,6 +3335,8 @@ static int __devinit ehea_probe_adapter(struct platform_device *dev,
 		goto out_shutdown_ports;
 	}
 
+	/* Handle any events that might be pending. */
+	tasklet_hi_schedule(&adapter->neq_tasklet);
 
 	ret = 0;
 	goto out;

drivers/net/ethernet/intel/e1000/e1000_main.c

@@ -3380,7 +3380,7 @@ static void e1000_dump(struct e1000_adapter *adapter)
 	for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
 		struct e1000_tx_desc *tx_desc = E1000_TX_DESC(*tx_ring, i);
 		struct e1000_buffer *buffer_info = &tx_ring->buffer_info[i];
-		struct my_u { u64 a; u64 b; };
+		struct my_u { __le64 a; __le64 b; };
 		struct my_u *u = (struct my_u *)tx_desc;
 		const char *type;
 
@@ -3424,7 +3424,7 @@ static void e1000_dump(struct e1000_adapter *adapter)
 	for (i = 0; rx_ring->desc && (i < rx_ring->count); i++) {
 		struct e1000_rx_desc *rx_desc = E1000_RX_DESC(*rx_ring, i);
 		struct e1000_buffer *buffer_info = &rx_ring->buffer_info[i];
-		struct my_u { u64 a; u64 b; };
+		struct my_u { __le64 a; __le64 b; };
 		struct my_u *u = (struct my_u *)rx_desc;
 		const char *type;
 

drivers/net/ethernet/intel/igb/igb_main.c

@@ -1111,9 +1111,12 @@ static int igb_set_interrupt_capability(struct igb_adapter *adapter)
 		adapter->flags |= IGB_FLAG_HAS_MSI;
 out:
 	/* Notify the stack of the (possibly) reduced queue counts. */
+	rtnl_lock();
 	netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues);
-	return netif_set_real_num_rx_queues(adapter->netdev,
-					    adapter->num_rx_queues);
+	err = netif_set_real_num_rx_queues(adapter->netdev,
+		adapter->num_rx_queues);
+	rtnl_unlock();
+	return err;
 }
 
 /**
@@ -2771,8 +2774,6 @@ void igb_configure_tx_ring(struct igb_adapter *adapter,
 
 	txdctl |= E1000_TXDCTL_QUEUE_ENABLE;
 	wr32(E1000_TXDCTL(reg_idx), txdctl);
-
-	netdev_tx_reset_queue(txring_txq(ring));
 }
 
 /**
@@ -3282,6 +3283,8 @@ static void igb_clean_tx_ring(struct igb_ring *tx_ring)
 		igb_unmap_and_free_tx_resource(tx_ring, buffer_info);
 	}
 
+	netdev_tx_reset_queue(txring_txq(tx_ring));
+
 	size = sizeof(struct igb_tx_buffer) * tx_ring->count;
 	memset(tx_ring->tx_buffer_info, 0, size);
 
@@ -6796,18 +6799,7 @@ static int igb_resume(struct device *dev)
 	pci_enable_wake(pdev, PCI_D3hot, 0);
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
-	if (!rtnl_is_locked()) {
-		/*
-		 * shut up ASSERT_RTNL() warning in
-		 * netif_set_real_num_tx/rx_queues.
-		 */
-		rtnl_lock();
-		err = igb_init_interrupt_scheme(adapter);
-		rtnl_unlock();
-	} else {
-		err = igb_init_interrupt_scheme(adapter);
-	}
-	if (err) {
+	if (igb_init_interrupt_scheme(adapter)) {
 		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
 	}

drivers/net/ethernet/intel/ixgbe/ixgbe.h

@@ -574,9 +574,6 @@ extern struct ixgbe_info ixgbe_82599_info;
 extern struct ixgbe_info ixgbe_X540_info;
 #ifdef CONFIG_IXGBE_DCB
 extern const struct dcbnl_rtnl_ops dcbnl_ops;
-extern int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *src_dcb_cfg,
-                              struct ixgbe_dcb_config *dst_dcb_cfg,
-                              int tc_max);
 #endif
 
 extern char ixgbe_driver_name[];

drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c

@@ -44,18 +44,26 @@
 #define DCB_NO_HW_CHG   1  /* DCB configuration did not change */
 #define DCB_HW_CHG      2  /* DCB configuration changed, no reset */
 
-int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *scfg,
-		       struct ixgbe_dcb_config *dcfg, int tc_max)
+static int ixgbe_copy_dcb_cfg(struct ixgbe_adapter *adapter, int tc_max)
 {
+	struct ixgbe_dcb_config *scfg = &adapter->temp_dcb_cfg;
+	struct ixgbe_dcb_config *dcfg = &adapter->dcb_cfg;
 	struct tc_configuration *src = NULL;
 	struct tc_configuration *dst = NULL;
 	int i, j;
 	int tx = DCB_TX_CONFIG;
 	int rx = DCB_RX_CONFIG;
 	int changes = 0;
+#ifdef IXGBE_FCOE
+	struct dcb_app app = {
+			      .selector = DCB_APP_IDTYPE_ETHTYPE,
+			      .protocol = ETH_P_FCOE,
+			     };
+	u8 up = dcb_getapp(adapter->netdev, &app);
 
-	if (!scfg || !dcfg)
-		return changes;
+	if (up && !(up & (1 << adapter->fcoe.up)))
+		changes |= BIT_APP_UPCHG;
+#endif
 
 	for (i = DCB_PG_ATTR_TC_0; i < tc_max + DCB_PG_ATTR_TC_0; i++) {
 		src = &scfg->tc_config[i - DCB_PG_ATTR_TC_0];
@@ -332,28 +340,12 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	int ret = DCB_NO_HW_CHG;
 	int i;
-#ifdef IXGBE_FCOE
-	struct dcb_app app = {
-			      .selector = DCB_APP_IDTYPE_ETHTYPE,
-			      .protocol = ETH_P_FCOE,
-			     };
-	u8 up;
-
-	/* In IEEE mode, use the IEEE Ethertype selector value */
-	if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) {
-		app.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE;
-		up = dcb_ieee_getapp_mask(netdev, &app);
-	} else {
-		up = dcb_getapp(netdev, &app);
-	}
-#endif
 
 	/* Fail command if not in CEE mode */
 	if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
 		return ret;
 
-	adapter->dcb_set_bitmap |= ixgbe_copy_dcb_cfg(&adapter->temp_dcb_cfg,
-						      &adapter->dcb_cfg,
+	adapter->dcb_set_bitmap |= ixgbe_copy_dcb_cfg(adapter,
 						      MAX_TRAFFIC_CLASS);
 	if (!adapter->dcb_set_bitmap)
 		return ret;
@@ -440,8 +432,13 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 	 * FCoE is using changes. This happens if the APP info
 	 * changes or the up2tc mapping is updated.
 	 */
-	if ((up && !(up & (1 << adapter->fcoe.up))) ||
-	    (adapter->dcb_set_bitmap & BIT_APP_UPCHG)) {
+	if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
+		struct dcb_app app = {
+				      .selector = DCB_APP_IDTYPE_ETHTYPE,
+				      .protocol = ETH_P_FCOE,
+				     };
+		u8 up = dcb_getapp(netdev, &app);
+
 		adapter->fcoe.up = ffs(up) - 1;
 		ixgbe_dcbnl_devreset(netdev);
 		ret = DCB_HW_CHG_RST;

drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c

@@ -1780,6 +1780,8 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring,
 		rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc);
 	}
 
+	netdev_tx_reset_queue(txring_txq(tx_ring));
+
 	/* re-map buffers to ring, store next to clean values */
 	ixgbe_alloc_rx_buffers(rx_ring, count);
 	rx_ring->next_to_clean = rx_ntc;