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.
  ...

11 files changed, 77 insertions, 59 deletions

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index e077d250872..6af310195ba 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/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);
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index c9069a28832..f4d2da0db1b 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/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;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 4348b6fd44f..37caa8885c2 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/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 @@ rx_ring_summary:
 	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;
 
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 5ec31598ee4..8683ca4748c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1111,9 +1111,12 @@ msi_only:
 		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;
 	}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 74e192107f9..81b15558953 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/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[];
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index 652e4b09546..32e5c02ff6d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/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;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 31a2bf76a34..cfe7d269590 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/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;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 88f6b2e9b72..467948e9ecd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2671,8 +2671,6 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter,
 	/* enable queue */
 	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), txdctl);
 
-	netdev_tx_reset_queue(txring_txq(ring));
-
 	/* TXDCTL.EN will return 0 on 82598 if link is down, so skip it */
 	if (hw->mac.type == ixgbe_mac_82598EB &&
 	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
@@ -4167,6 +4165,8 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring)
 		ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
 	}
 
+	netdev_tx_reset_queue(txring_txq(tx_ring));
+
 	size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
 	memset(tx_ring->tx_buffer_info, 0, size);
 
@@ -4418,8 +4418,8 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
 	adapter->dcb_cfg.pfc_mode_enable = false;
 	adapter->dcb_set_bitmap = 0x00;
 	adapter->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_CEE;
-	ixgbe_copy_dcb_cfg(&adapter->dcb_cfg, &adapter->temp_dcb_cfg,
-			   MAX_TRAFFIC_CLASS);
+	memcpy(&adapter->temp_dcb_cfg, &adapter->dcb_cfg,
+	       sizeof(adapter->temp_dcb_cfg));
 
 #endif
 
@@ -4866,10 +4866,12 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	netif_device_detach(netdev);
 
 	if (netif_running(netdev)) {
+		rtnl_lock();
 		ixgbe_down(adapter);
 		ixgbe_free_irq(adapter);
 		ixgbe_free_all_tx_resources(adapter);
 		ixgbe_free_all_rx_resources(adapter);
+		rtnl_unlock();
 	}
 
 	ixgbe_clear_interrupt_scheme(adapter);
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index f8dda009d3c..5e313e9a252 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -618,10 +618,8 @@ static void ks8851_irq_work(struct work_struct *work)
 	netif_dbg(ks, intr, ks->netdev,
 		  "%s: status 0x%04x\n", __func__, status);
 
-	if (status & IRQ_LCI) {
-		/* should do something about checking link status */
+	if (status & IRQ_LCI)
 		handled |= IRQ_LCI;
-	}
 
 	if (status & IRQ_LDI) {
 		u16 pmecr = ks8851_rdreg16(ks, KS_PMECR);
@@ -684,6 +682,9 @@ static void ks8851_irq_work(struct work_struct *work)
 
 	mutex_unlock(&ks->lock);
 
+	if (status & IRQ_LCI)
+		mii_check_link(&ks->mii);
+
 	if (status & IRQ_TXI)
 		netif_wake_queue(ks->netdev);
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f54509377ef..ce6b44d1f25 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -61,8 +61,12 @@
 #define R8169_MSG_DEFAULT \
 	(NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN)
 
-#define TX_BUFFS_AVAIL(tp) \
-	(tp->dirty_tx + NUM_TX_DESC - tp->cur_tx - 1)
+#define TX_SLOTS_AVAIL(tp) \
+	(tp->dirty_tx + NUM_TX_DESC - tp->cur_tx)
+
+/* A skbuff with nr_frags needs nr_frags+1 entries in the tx queue */
+#define TX_FRAGS_READY_FOR(tp,nr_frags) \
+	(TX_SLOTS_AVAIL(tp) >= (nr_frags + 1))
 
 /* Maximum number of multicast addresses to filter (vs. Rx-all-multicast).
    The RTL chips use a 64 element hash table based on the Ethernet CRC. */
@@ -5115,7 +5119,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	u32 opts[2];
 	int frags;
 
-	if (unlikely(TX_BUFFS_AVAIL(tp) < skb_shinfo(skb)->nr_frags)) {
+	if (unlikely(!TX_FRAGS_READY_FOR(tp, skb_shinfo(skb)->nr_frags))) {
 		netif_err(tp, drv, dev, "BUG! Tx Ring full when queue awake!\n");
 		goto err_stop_0;
 	}
@@ -5169,7 +5173,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	mmiowb();
 
-	if (TX_BUFFS_AVAIL(tp) < MAX_SKB_FRAGS) {
+	if (!TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS)) {
 		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
 		 * not miss a ring update when it notices a stopped queue.
 		 */
@@ -5183,7 +5187,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 		 * can't.
 		 */
 		smp_mb();
-		if (TX_BUFFS_AVAIL(tp) >= MAX_SKB_FRAGS)
+		if (TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS))
 			netif_wake_queue(dev);
 	}
 
@@ -5306,7 +5310,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 		 */
 		smp_mb();
 		if (netif_queue_stopped(dev) &&
-		    (TX_BUFFS_AVAIL(tp) >= MAX_SKB_FRAGS)) {
+		    TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS)) {
 			netif_wake_queue(dev);
 		}
 		/*
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 3cbfbffe3f0..4a0005342e6 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1349,7 +1349,7 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 	}
 
 	/* RSS might be usable on VFs even if it is disabled on the PF */
-	efx->rss_spread = (efx->n_rx_channels > 1 ?
+	efx->rss_spread = ((efx->n_rx_channels > 1 || !efx_sriov_wanted(efx)) ?
 			   efx->n_rx_channels : efx_vf_size(efx));
 
 	return 0;