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

Pull networking fixes from David Miller:
 "Mostly small sets of driver fixes scattered all over the place.

   1) Mediatek driver fixes from Sean Wang.  Forward port not written
      correctly during TX map, missed handling of EPROBE_DEFER, and
      mistaken use of put_page() instead of skb_free_frag().

   2) Fix socket double-free in KCM code, from WANG Cong.

   3) QED driver fixes from Sudarsana Reddy Kalluru, including a fix for
      using the dcbx buffers before initializing them.

   4) Mellanox Switch driver fixes from Jiri Pirko, including a fix for
      double fib removals and an error handling fix in
      mlxsw_sp_module_init().

   5) Fix kernel panic when enabling LLDP in i40e driver, from Dave
      Ertman.

   6) Fix padding of TSO packets in thunderx driver, from Sunil Goutham.

   7) TCP's rcv_wup not initialized properly when using fastopen, from
      Neal Cardwell.

   8) Don't use uninitialized flow keys in flow dissector, from Gao
      Feng.

   9) Use after free in l2tp module unload, from Sabrina Dubroca.

  10) Fix interrupt registry ordering issues in smsc911x driver, from
      Jeremy Linton.

  11) Fix crashes in bonding having to do with enslaving and rx_handler,
      from Mahesh Bandewar.

  12) AF_UNIX deadlock fixes from Linus.

  13) In mlx5 driver, don't read skb->xmit_mode after it might have been
      freed from the TX reclaim path.  From Tariq Toukan.

  14) Fix a bug from 2015 in TCP Yeah where the congestion window does
      not increase, from Artem Germanov.

  15) Don't pad frames on receive in NFP driver, from Jakub Kicinski.

  16) Fix chunk fragmenting in SCTP wrt. GSO, from Marcelo Ricardo
      Leitner.

  17) Fix deletion of VRF routes, from Mark Tomlinson.

  18) Fix device refcount leak when DAD fails in ipv6, from Wei Yongjun"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (101 commits)
  net/mlx4_en: Fix panic on xmit while port is down
  net/mlx4_en: Fixes for DCBX
  net/mlx4_en: Fix the return value of mlx4_en_dcbnl_set_state()
  net/mlx4_en: Fix the return value of mlx4_en_dcbnl_set_all()
  net: ethernet: renesas: sh_eth: add POST registers for rz
  drivers: net: phy: mdio-xgene: Add hardware dependency
  dwc_eth_qos: do not register semi-initialized device
  sctp: identify chunks that need to be fragmented at IP level
  mlxsw: spectrum: Set port type before setting its address
  mlxsw: spectrum_router: Fix error path in mlxsw_sp_router_init
  nfp: don't pad frames on receive
  nfp: drop support for old firmware ABIs
  nfp: remove linux/version.h includes
  tcp: cwnd does not increase in TCP YeAH
  net/mlx5e: Fix parsing of vlan packets when updating lro header
  net/mlx5e: Fix global PFC counters replication
  net/mlx5e: Prevent casting overflow
  net/mlx5e: Move an_disable_cap bit to a new position
  net/mlx5e: Fix xmit_more counter race issue
  tcp: fastopen: avoid negative sk_forward_alloc
  ...

MAINTAINERS

@@ -2485,7 +2485,7 @@ F:	include/net/bluetooth/
 BONDING DRIVER
 M:	Jay Vosburgh <[email protected]>
 M:	Veaceslav Falico <[email protected]>
-M:	Andy Gospodarek <[email protected]>
+M:	Andy Gospodarek <[email protected]>
 L:	[email protected]
 W:	http://sourceforge.net/projects/bonding/
 S:	Supported
@@ -3269,7 +3269,7 @@ S:	Maintained
 F:	drivers/net/wan/cosa*
 
 CPMAC ETHERNET DRIVER
-M:	Florian Fainelli <[email protected]>
+M:	Florian Fainelli <[email protected]>
 L:	[email protected]
 S:	Maintained
 F:	drivers/net/ethernet/ti/cpmac.c

drivers/net/bonding/bond_main.c

@@ -1341,9 +1341,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 			    slave_dev->name);
 	}
 
-	/* already enslaved */
-	if (slave_dev->flags & IFF_SLAVE) {
-		netdev_dbg(bond_dev, "Error: Device was already enslaved\n");
+	/* already in-use? */
+	if (netdev_is_rx_handler_busy(slave_dev)) {
+		netdev_err(bond_dev,
+			   "Error: Device is in use and cannot be enslaved\n");
 		return -EBUSY;
 	}
 

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

@@ -772,6 +772,11 @@ void bnx2x_fw_dump_lvl(struct bnx2x *bp, const char *lvl)
 		(bp->common.bc_ver & 0xff00) >> 8,
 		(bp->common.bc_ver & 0xff));
 
+	if (pci_channel_offline(bp->pdev)) {
+		BNX2X_ERR("Cannot dump MCP info while in PCI error\n");
+		return;
+	}
+
 	val = REG_RD(bp, MCP_REG_MCPR_CPU_PROGRAM_COUNTER);
 	if (val == REG_RD(bp, MCP_REG_MCPR_CPU_PROGRAM_COUNTER))
 		BNX2X_ERR("%s" "MCP PC at 0x%x\n", lvl, val);
@@ -9415,10 +9420,16 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link)
 	/* Release IRQs */
 	bnx2x_free_irq(bp);
 
-	/* Reset the chip */
-	rc = bnx2x_reset_hw(bp, reset_code);
-	if (rc)
-		BNX2X_ERR("HW_RESET failed\n");
+	/* Reset the chip, unless PCI function is offline. If we reach this
+	 * point following a PCI error handling, it means device is really
+	 * in a bad state and we're about to remove it, so reset the chip
+	 * is not a good idea.
+	 */
+	if (!pci_channel_offline(bp->pdev)) {
+		rc = bnx2x_reset_hw(bp, reset_code);
+		if (rc)
+			BNX2X_ERR("HW_RESET failed\n");
+	}
 
 	/* Report UNLOAD_DONE to MCP */
 	bnx2x_send_unload_done(bp, keep_link);

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -353,8 +353,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		push_len = (length + sizeof(*tx_push) + 7) / 8;
 		if (push_len > 16) {
 			__iowrite64_copy(txr->tx_doorbell, tx_push_buf, 16);
-			__iowrite64_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
-					 push_len - 16);
+			__iowrite32_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
+					 (push_len - 16) << 1);
 		} else {
 			__iowrite64_copy(txr->tx_doorbell, tx_push_buf,
 					 push_len);

drivers/net/ethernet/broadcom/tg3.c

@@ -14012,6 +14012,7 @@ static int tg3_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	if ((ec->rx_coalesce_usecs > MAX_RXCOL_TICKS) ||
 	    (!ec->rx_coalesce_usecs) ||
 	    (ec->tx_coalesce_usecs > MAX_TXCOL_TICKS) ||
+	    (!ec->tx_coalesce_usecs) ||
 	    (ec->rx_max_coalesced_frames > MAX_RXMAX_FRAMES) ||
 	    (ec->tx_max_coalesced_frames > MAX_TXMAX_FRAMES) ||
 	    (ec->rx_coalesce_usecs_irq > max_rxcoal_tick_int) ||
@@ -14022,16 +14023,6 @@ static int tg3_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	    (ec->stats_block_coalesce_usecs < min_stat_coal_ticks))
 		return -EINVAL;
 
-	/* No rx interrupts will be generated if both are zero */
-	if ((ec->rx_coalesce_usecs == 0) &&
-	    (ec->rx_max_coalesced_frames == 0))
-		return -EINVAL;
-
-	/* No tx interrupts will be generated if both are zero */
-	if ((ec->tx_coalesce_usecs == 0) &&
-	    (ec->tx_max_coalesced_frames == 0))
-		return -EINVAL;
-
 	/* Only copy relevant parameters, ignore all others. */
 	tp->coal.rx_coalesce_usecs = ec->rx_coalesce_usecs;
 	tp->coal.tx_coalesce_usecs = ec->tx_coalesce_usecs;

drivers/net/ethernet/cadence/macb.c

@@ -1323,6 +1323,24 @@ static unsigned int macb_tx_map(struct macb *bp,
 	return 0;
 }
 
+static inline int macb_clear_csum(struct sk_buff *skb)
+{
+	/* no change for packets without checksum offloading */
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	/* make sure we can modify the header */
+	if (unlikely(skb_cow_head(skb, 0)))
+		return -1;
+
+	/* initialize checksum field
+	 * This is required - at least for Zynq, which otherwise calculates
+	 * wrong UDP header checksums for UDP packets with UDP data len <=2
+	 */
+	*(__sum16 *)(skb_checksum_start(skb) + skb->csum_offset) = 0;
+	return 0;
+}
+
 static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	u16 queue_index = skb_get_queue_mapping(skb);
@@ -1362,6 +1380,11 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
+	if (macb_clear_csum(skb)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
 	/* Map socket buffer for DMA transfer */
 	if (!macb_tx_map(bp, queue, skb)) {
 		dev_kfree_skb_any(skb);

drivers/net/ethernet/cavium/thunder/nic.h

@@ -279,6 +279,7 @@ struct nicvf {
 	u8			sqs_id;
 	bool                    sqs_mode;
 	bool			hw_tso;
+	bool			t88;
 
 	/* Receive buffer alloc */
 	u32			rb_page_offset;

drivers/net/ethernet/cavium/thunder/nic_main.c

@@ -251,9 +251,14 @@ static void nic_set_tx_pkt_pad(struct nicpf *nic, int size)
 	int lmac;
 	u64 lmac_cfg;
 
-	/* Max value that can be set is 60 */
-	if (size > 60)
-		size = 60;
+	/* There is a issue in HW where-in while sending GSO sized
+	 * pkts as part of TSO, if pkt len falls below this size
+	 * NIC will zero PAD packet and also updates IP total length.
+	 * Hence set this value to lessthan min pkt size of MAC+IP+TCP
+	 * headers, BGX will do the padding to transmit 64 byte pkt.
+	 */
+	if (size > 52)
+		size = 52;
 
 	for (lmac = 0; lmac < (MAX_BGX_PER_CN88XX * MAX_LMAC_PER_BGX); lmac++) {
 		lmac_cfg = nic_reg_read(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3));

drivers/net/ethernet/cavium/thunder/nicvf_main.c

@@ -513,6 +513,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 	struct nicvf *nic = netdev_priv(netdev);
 	struct snd_queue *sq;
 	struct sq_hdr_subdesc *hdr;
+	struct sq_hdr_subdesc *tso_sqe;
 
 	sq = &nic->qs->sq[cqe_tx->sq_idx];
 
@@ -527,17 +528,21 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 
 	nicvf_check_cqe_tx_errs(nic, cq, cqe_tx);
 	skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr];
-	/* For TSO offloaded packets only one SQE will have a valid SKB */
 	if (skb) {
+		/* Check for dummy descriptor used for HW TSO offload on 88xx */
+		if (hdr->dont_send) {
+			/* Get actual TSO descriptors and free them */
+			tso_sqe =
+			 (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
+			nicvf_put_sq_desc(sq, tso_sqe->subdesc_cnt + 1);
+		}
 		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
 		prefetch(skb);
 		dev_consume_skb_any(skb);
 		sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
 	} else {
-		/* In case of HW TSO, HW sends a CQE for each segment of a TSO
-		 * packet instead of a single CQE for the whole TSO packet
-		 * transmitted. Each of this CQE points to the same SQE, so
-		 * avoid freeing same SQE multiple times.
+		/* In case of SW TSO on 88xx, only last segment will have
+		 * a SKB attached, so just free SQEs here.
 		 */
 		if (!nic->hw_tso)
 			nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
@@ -1502,6 +1507,7 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct net_device *netdev;
 	struct nicvf *nic;
 	int    err, qcount;
+	u16    sdevid;
 
 	err = pci_enable_device(pdev);
 	if (err) {
@@ -1575,6 +1581,10 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!pass1_silicon(nic->pdev))
 		nic->hw_tso = true;
 
+	pci_read_config_word(nic->pdev, PCI_SUBSYSTEM_ID, &sdevid);
+	if (sdevid == 0xA134)
+		nic->t88 = true;
+
 	/* Check if this VF is in QS only mode */
 	if (nic->sqs_mode)
 		return 0;

drivers/net/ethernet/cavium/thunder/nicvf_queues.c

@@ -938,6 +938,8 @@ static int nicvf_tso_count_subdescs(struct sk_buff *skb)
 	return num_edescs + sh->gso_segs;
 }
 
+#define POST_CQE_DESC_COUNT 2
+
 /* Get the number of SQ descriptors needed to xmit this skb */
 static int nicvf_sq_subdesc_required(struct nicvf *nic, struct sk_buff *skb)
 {
@@ -948,6 +950,10 @@ static int nicvf_sq_subdesc_required(struct nicvf *nic, struct sk_buff *skb)
 		return subdesc_cnt;
 	}
 
+	/* Dummy descriptors to get TSO pkt completion notification */
+	if (nic->t88 && nic->hw_tso && skb_shinfo(skb)->gso_size)
+		subdesc_cnt += POST_CQE_DESC_COUNT;
+
 	if (skb_shinfo(skb)->nr_frags)
 		subdesc_cnt += skb_shinfo(skb)->nr_frags;
 
@@ -965,14 +971,21 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 	struct sq_hdr_subdesc *hdr;
 
 	hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
-	sq->skbuff[qentry] = (u64)skb;
-
 	memset(hdr, 0, SND_QUEUE_DESC_SIZE);
 	hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
-	/* Enable notification via CQE after processing SQE */
-	hdr->post_cqe = 1;
-	/* No of subdescriptors following this */
-	hdr->subdesc_cnt = subdesc_cnt;
+
+	if (nic->t88 && nic->hw_tso && skb_shinfo(skb)->gso_size) {
+		/* post_cqe = 0, to avoid HW posting a CQE for every TSO
+		 * segment transmitted on 88xx.
+		 */
+		hdr->subdesc_cnt = subdesc_cnt - POST_CQE_DESC_COUNT;
+	} else {
+		sq->skbuff[qentry] = (u64)skb;
+		/* Enable notification via CQE after processing SQE */
+		hdr->post_cqe = 1;
+		/* No of subdescriptors following this */
+		hdr->subdesc_cnt = subdesc_cnt;
+	}
 	hdr->tot_len = len;
 
 	/* Offload checksum calculation to HW */
@@ -1023,6 +1036,37 @@ static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry,
 	gather->addr = data;
 }
 
+/* Add HDR + IMMEDIATE subdescriptors right after descriptors of a TSO
+ * packet so that a CQE is posted as a notifation for transmission of
+ * TSO packet.
+ */
+static inline void nicvf_sq_add_cqe_subdesc(struct snd_queue *sq, int qentry,
+					    int tso_sqe, struct sk_buff *skb)
+{
+	struct sq_imm_subdesc *imm;
+	struct sq_hdr_subdesc *hdr;
+
+	sq->skbuff[qentry] = (u64)skb;
+
+	hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
+	memset(hdr, 0, SND_QUEUE_DESC_SIZE);
+	hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
+	/* Enable notification via CQE after processing SQE */
+	hdr->post_cqe = 1;
+	/* There is no packet to transmit here */
+	hdr->dont_send = 1;
+	hdr->subdesc_cnt = POST_CQE_DESC_COUNT - 1;
+	hdr->tot_len = 1;
+	/* Actual TSO header SQE index, needed for cleanup */
+	hdr->rsvd2 = tso_sqe;
+
+	qentry = nicvf_get_nxt_sqentry(sq, qentry);
+	imm = (struct sq_imm_subdesc *)GET_SQ_DESC(sq, qentry);
+	memset(imm, 0, SND_QUEUE_DESC_SIZE);
+	imm->subdesc_type = SQ_DESC_TYPE_IMMEDIATE;
+	imm->len = 1;
+}
+
 /* Segment a TSO packet into 'gso_size' segments and append
  * them to SQ for transfer
  */
@@ -1096,7 +1140,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb)
 {
 	int i, size;
-	int subdesc_cnt;
+	int subdesc_cnt, tso_sqe = 0;
 	int sq_num, qentry;
 	struct queue_set *qs;
 	struct snd_queue *sq;
@@ -1131,6 +1175,7 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb)
 	/* Add SQ header subdesc */
 	nicvf_sq_add_hdr_subdesc(nic, sq, qentry, subdesc_cnt - 1,
 				 skb, skb->len);
+	tso_sqe = qentry;
 
 	/* Add SQ gather subdescs */
 	qentry = nicvf_get_nxt_sqentry(sq, qentry);
@@ -1154,6 +1199,11 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb)
 	}
 
 doorbell:
+	if (nic->t88 && skb_shinfo(skb)->gso_size) {
+		qentry = nicvf_get_nxt_sqentry(sq, qentry);
+		nicvf_sq_add_cqe_subdesc(sq, qentry, tso_sqe, skb);
+	}
+
 	/* make sure all memory stores are done before ringing doorbell */
 	smp_wmb();
 

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -5113,9 +5113,13 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 				       DCB_CAP_DCBX_VER_IEEE;
 
 			pf->flags |= I40E_FLAG_DCB_CAPABLE;
-			/* Enable DCB tagging only when more than one TC */
+			/* Enable DCB tagging only when more than one TC
+			 * or explicitly disable if only one TC
+			 */
 			if (i40e_dcb_get_num_tc(&hw->local_dcbx_config) > 1)
 				pf->flags |= I40E_FLAG_DCB_ENABLED;
+			else
+				pf->flags &= ~I40E_FLAG_DCB_ENABLED;
 			dev_dbg(&pf->pdev->dev,
 				"DCBX offload is supported for this PF.\n");
 		}
@@ -5716,7 +5720,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	u8 type;
 
 	/* Not DCB capable or capability disabled */
-	if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
+	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
 		return ret;
 
 	/* Ignore if event is not for Nearest Bridge */
@@ -7896,6 +7900,7 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf)
 #endif
 				       I40E_FLAG_RSS_ENABLED	|
 				       I40E_FLAG_DCB_CAPABLE	|
+				       I40E_FLAG_DCB_ENABLED	|
 				       I40E_FLAG_SRIOV_ENABLED	|
 				       I40E_FLAG_FD_SB_ENABLED	|
 				       I40E_FLAG_FD_ATR_ENABLED	|
@@ -10502,6 +10507,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 			       I40E_FLAG_FD_SB_ENABLED	|
 			       I40E_FLAG_FD_ATR_ENABLED	|
 			       I40E_FLAG_DCB_CAPABLE	|
+			       I40E_FLAG_DCB_ENABLED	|
 			       I40E_FLAG_SRIOV_ENABLED	|
 			       I40E_FLAG_VMDQ_ENABLED);
 	} else if (!(pf->flags & (I40E_FLAG_RSS_ENABLED |
@@ -10525,7 +10531,8 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		/* Not enough queues for all TCs */
 		if ((pf->flags & I40E_FLAG_DCB_CAPABLE) &&
 		    (queues_left < I40E_MAX_TRAFFIC_CLASS)) {
-			pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+			pf->flags &= ~(I40E_FLAG_DCB_CAPABLE |
+					I40E_FLAG_DCB_ENABLED);
 			dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n");
 		}
 		pf->num_lan_qps = max_t(int, pf->rss_size_max,
@@ -10922,7 +10929,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = i40e_init_pf_dcb(pf);
 	if (err) {
 		dev_info(&pdev->dev, "DCB init failed %d, disabled\n", err);
-		pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+		pf->flags &= ~(I40E_FLAG_DCB_CAPABLE & I40E_FLAG_DCB_ENABLED);
 		/* Continue without DCB enabled */
 	}
 #endif /* CONFIG_I40E_DCB */