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

Pull networking updates from David Miller:

 1) Make syn floods consume significantly less resources by

    a) Not pre-COW'ing routing metrics for SYN/ACKs
    b) Mirroring the device queue mapping of the SYN for the SYN/ACK
       reply.

    Both from Eric Dumazet.

 2) Fix calculation errors in Byte Queue Limiting, from Hiroaki SHIMODA.

 3) Validate the length requested when building a paged SKB for a
    socket, so we don't overrun the page vector accidently.  From Jason
    Wang.

 4) When netlabel is disabled, we abort all IP option processing when we
    see a CIPSO option.  This isn't the right thing to do, we should
    simply skip over it and continue processing the remaining options
    (if any).  Fix from Paul Moore.

 5) SRIOV fixes for the mellanox driver from Jack orgenstein and Marcel
    Apfelbaum.

 6) 8139cp enables the receiver before the ring address is properly
    programmed, which potentially lets the device crap over random
    memory.  Fix from Jason Wang.

 7) e1000/e1000e fixes for i217 RST handling, and an improper buffer
    address reference in jumbo RX frame processing from Bruce Allan and
    Sebastian Andrzej Siewior, respectively.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  fec_mpc52xx: fix timestamp filtering
  mcs7830: Implement link state detection
  e1000e: fix Rapid Start Technology support for i217
  e1000: look into the page instead of skb->data for e1000_tbi_adjust_stats()
  r8169: call netif_napi_del at errpaths and at driver unload
  tcp: reflect SYN queue_mapping into SYNACK packets
  tcp: do not create inetpeer on SYNACK message
  8139cp/8139too: terminate the eeprom access with the right opmode
  8139cp: set ring address before enabling receiver
  cipso: handle CIPSO options correctly when NetLabel is disabled
  net: sock: validate data_len before allocating skb in sock_alloc_send_pskb()
  bql: Avoid possible inconsistent calculation.
  bql: Avoid unneeded limit decrement.
  bql: Fix POSDIFF() to integer overflow aware.
  net/mlx4_core: Fix obscure mlx4_cmd_box parameter in QUERY_DEV_CAP
  net/mlx4_core: Check port out-of-range before using in mlx4_slave_cap
  net/mlx4_core: Fixes for VF / Guest startup flow
  net/mlx4_en: Fix improper use of "port" parameter in mlx4_en_event
  net/mlx4_core: Fix number of EQs used in ICM initialisation
  net/mlx4_core: Fix the slave_id out-of-range test in mlx4_eq_int

Author: torvalds

drivers/net/ethernet/freescale/fec_mpc52xx.c

@@ -437,7 +437,7 @@ static irqreturn_t mpc52xx_fec_rx_interrupt(int irq, void *dev_id)
 		length = status & BCOM_FEC_RX_BD_LEN_MASK;
 		skb_put(rskb, length - 4);	/* length without CRC32 */
 		rskb->protocol = eth_type_trans(rskb, dev);
-		if (!skb_defer_rx_timestamp(skb))
+		if (!skb_defer_rx_timestamp(rskb))
 			netif_rx(rskb);
 
 		spin_lock(&priv->lock);

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

@@ -4080,7 +4080,7 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter,
 				spin_lock_irqsave(&adapter->stats_lock,
 				                  irq_flags);
 				e1000_tbi_adjust_stats(hw, &adapter->stats,
-				                       length, skb->data);
+						       length, mapped);
 				spin_unlock_irqrestore(&adapter->stats_lock,
 				                       irq_flags);
 				length--;

drivers/net/ethernet/intel/e1000e/ich8lan.c

@@ -165,14 +165,14 @@
 #define I217_EEE_100_SUPPORTED  (1 << 1)	/* 100BaseTx EEE supported */
 
 /* Intel Rapid Start Technology Support */
-#define I217_PROXY_CTRL                 PHY_REG(BM_WUC_PAGE, 70)
+#define I217_PROXY_CTRL                 BM_PHY_REG(BM_WUC_PAGE, 70)
 #define I217_PROXY_CTRL_AUTO_DISABLE    0x0080
 #define I217_SxCTRL                     PHY_REG(BM_PORT_CTRL_PAGE, 28)
-#define I217_SxCTRL_MASK                0x1000
+#define I217_SxCTRL_ENABLE_LPI_RESET    0x1000
 #define I217_CGFREG                     PHY_REG(772, 29)
-#define I217_CGFREG_MASK                0x0002
+#define I217_CGFREG_ENABLE_MTA_RESET    0x0002
 #define I217_MEMPWR                     PHY_REG(772, 26)
-#define I217_MEMPWR_MASK                0x0010
+#define I217_MEMPWR_DISABLE_SMB_RELEASE 0x0010
 
 /* Strapping Option Register - RO */
 #define E1000_STRAP                     0x0000C
@@ -4089,12 +4089,12 @@ void e1000_suspend_workarounds_ich8lan(struct e1000_hw *hw)
 			 * power good.
 			 */
 			e1e_rphy_locked(hw, I217_SxCTRL, &phy_reg);
-			phy_reg |= I217_SxCTRL_MASK;
+			phy_reg |= I217_SxCTRL_ENABLE_LPI_RESET;
 			e1e_wphy_locked(hw, I217_SxCTRL, phy_reg);
 
 			/* Disable the SMB release on LCD reset. */
 			e1e_rphy_locked(hw, I217_MEMPWR, &phy_reg);
-			phy_reg &= ~I217_MEMPWR;
+			phy_reg &= ~I217_MEMPWR_DISABLE_SMB_RELEASE;
 			e1e_wphy_locked(hw, I217_MEMPWR, phy_reg);
 		}
 
@@ -4103,7 +4103,7 @@ void e1000_suspend_workarounds_ich8lan(struct e1000_hw *hw)
 		 * Support
 		 */
 		e1e_rphy_locked(hw, I217_CGFREG, &phy_reg);
-		phy_reg |= I217_CGFREG_MASK;
+		phy_reg |= I217_CGFREG_ENABLE_MTA_RESET;
 		e1e_wphy_locked(hw, I217_CGFREG, phy_reg);
 
 release:
@@ -4176,7 +4176,7 @@ void e1000_resume_workarounds_pchlan(struct e1000_hw *hw)
 			ret_val = e1e_rphy_locked(hw, I217_MEMPWR, &phy_reg);
 			if (ret_val)
 				goto release;
-			phy_reg |= I217_MEMPWR_MASK;
+			phy_reg |= I217_MEMPWR_DISABLE_SMB_RELEASE;
 			e1e_wphy_locked(hw, I217_MEMPWR, phy_reg);
 
 			/* Disable Proxy */
@@ -4186,7 +4186,7 @@ void e1000_resume_workarounds_pchlan(struct e1000_hw *hw)
 		ret_val = e1e_rphy_locked(hw, I217_CGFREG, &phy_reg);
 		if (ret_val)
 			goto release;
-		phy_reg &= ~I217_CGFREG_MASK;
+		phy_reg &= ~I217_CGFREG_ENABLE_MTA_RESET;
 		e1e_wphy_locked(hw, I217_CGFREG, phy_reg);
 release:
 		if (ret_val)

drivers/net/ethernet/mellanox/mlx4/cmd.c

@@ -617,7 +617,7 @@ static struct mlx4_cmd_info cmd_info[] = {
 		.out_is_imm = false,
 		.encode_slave_id = false,
 		.verify = NULL,
-		.wrapper = NULL
+		.wrapper = mlx4_QUERY_FW_wrapper
 	},
 	{
 		.opcode = MLX4_CMD_QUERY_HCA,
@@ -635,7 +635,7 @@ static struct mlx4_cmd_info cmd_info[] = {
 		.out_is_imm = false,
 		.encode_slave_id = false,
 		.verify = NULL,
-		.wrapper = NULL
+		.wrapper = mlx4_QUERY_DEV_CAP_wrapper
 	},
 	{
 		.opcode = MLX4_CMD_QUERY_FUNC_CAP,

drivers/net/ethernet/mellanox/mlx4/en_main.c

@@ -136,13 +136,12 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 	struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr;
 	struct mlx4_en_priv *priv;
 
-	if (!mdev->pndev[port])
-		return;
-
-	priv = netdev_priv(mdev->pndev[port]);
 	switch (event) {
 	case MLX4_DEV_EVENT_PORT_UP:
 	case MLX4_DEV_EVENT_PORT_DOWN:
+		if (!mdev->pndev[port])
+			return;
+		priv = netdev_priv(mdev->pndev[port]);
 		/* To prevent races, we poll the link state in a separate
 		  task rather than changing it here */
 		priv->link_state = event;
@@ -154,7 +153,10 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 		break;
 
 	default:
-		mlx4_warn(mdev, "Unhandled event: %d\n", event);
+		if (port < 1 || port > dev->caps.num_ports ||
+		    !mdev->pndev[port])
+			return;
+		mlx4_warn(mdev, "Unhandled event %d for port %d\n", event, port);
 	}
 }
 

drivers/net/ethernet/mellanox/mlx4/eq.c

@@ -426,7 +426,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 			mlx4_dbg(dev, "FLR event for slave: %d\n", flr_slave);
 
-			if (flr_slave > dev->num_slaves) {
+			if (flr_slave >= dev->num_slaves) {
 				mlx4_warn(dev,
 					  "Got FLR for unknown function: %d\n",
 					  flr_slave);

drivers/net/ethernet/mellanox/mlx4/fw.c

@@ -412,7 +412,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	outbox = mailbox->buf;
 
 	err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
-			   MLX4_CMD_TIME_CLASS_A, !mlx4_is_slave(dev));
+			   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 	if (err)
 		goto out;
 
@@ -590,8 +590,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 		for (i = 1; i <= dev_cap->num_ports; ++i) {
 			err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 0, MLX4_CMD_QUERY_PORT,
-					   MLX4_CMD_TIME_CLASS_B,
-					   !mlx4_is_slave(dev));
+					   MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 			if (err)
 				goto out;
 
@@ -669,6 +668,28 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	return err;
 }
 
+int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
+			       struct mlx4_vhcr *vhcr,
+			       struct mlx4_cmd_mailbox *inbox,
+			       struct mlx4_cmd_mailbox *outbox,
+			       struct mlx4_cmd_info *cmd)
+{
+	int	err = 0;
+	u8	field;
+
+	err = mlx4_cmd_box(dev, 0, outbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
+			   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+	if (err)
+		return err;
+
+	/* For guests, report Blueflame disabled */
+	MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_BF_OFFSET);
+	field &= 0x7f;
+	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET);
+
+	return 0;
+}
+
 int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			    struct mlx4_vhcr *vhcr,
 			    struct mlx4_cmd_mailbox *inbox,
@@ -860,6 +881,9 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
 		((fw_ver & 0xffff0000ull) >> 16) |
 		((fw_ver & 0x0000ffffull) << 16);
 
+	if (mlx4_is_slave(dev))
+		goto out;
+
 	MLX4_GET(lg, outbox, QUERY_FW_PPF_ID);
 	dev->caps.function = lg;
 
@@ -927,6 +951,27 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
 	return err;
 }
 
+int mlx4_QUERY_FW_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	u8 *outbuf;
+	int err;
+
+	outbuf = outbox->buf;
+	err = mlx4_cmd_box(dev, 0, outbox->dma, 0, 0, MLX4_CMD_QUERY_FW,
+			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+	if (err)
+		return err;
+
+	/* for slaves, zero out everything except FW version */
+	outbuf[0] = outbuf[1] = 0;
+	memset(&outbuf[8], 0, QUERY_FW_OUT_SIZE - 8);
+	return 0;
+}
+
 static void get_board_id(void *vsd, char *board_id)
 {
 	int i;

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -142,12 +142,6 @@ struct mlx4_port_config {
 	struct pci_dev *pdev;
 };
 
-static inline int mlx4_master_get_num_eqs(struct mlx4_dev *dev)
-{
-	return dev->caps.reserved_eqs +
-		MLX4_MFUNC_EQ_NUM * (dev->num_slaves + 1);
-}
-
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
 {
@@ -217,6 +211,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	}
 
 	dev->caps.num_ports	     = dev_cap->num_ports;
+	dev->phys_caps.num_phys_eqs  = MLX4_MAX_EQ_NUM;
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		dev->caps.vl_cap[i]	    = dev_cap->max_vl[i];
 		dev->caps.ib_mtu_cap[i]	    = dev_cap->ib_mtu[i];
@@ -435,12 +430,17 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz;
 
 	memset(&dev_cap, 0, sizeof(dev_cap));
+	dev->caps.max_qp_dest_rdma = 1 << hca_param.log_rd_per_qp;
 	err = mlx4_dev_cap(dev, &dev_cap);
 	if (err) {
 		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
 		return err;
 	}
 
+	err = mlx4_QUERY_FW(dev);
+	if (err)
+		mlx4_err(dev, "QUERY_FW command failed: could not get FW version.\n");
+
 	page_size = ~dev->caps.page_size_cap + 1;
 	mlx4_warn(dev, "HCA minimum page size:%d\n", page_size);
 	if (page_size > PAGE_SIZE) {
@@ -485,15 +485,15 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	dev->caps.num_mgms              = 0;
 	dev->caps.num_amgms             = 0;
 
-	for (i = 1; i <= dev->caps.num_ports; ++i)
-		dev->caps.port_mask[i] = dev->caps.port_type[i];
-
 	if (dev->caps.num_ports > MLX4_MAX_PORTS) {
 		mlx4_err(dev, "HCA has %d ports, but we only support %d, "
 			 "aborting.\n", dev->caps.num_ports, MLX4_MAX_PORTS);
 		return -ENODEV;
 	}
 
+	for (i = 1; i <= dev->caps.num_ports; ++i)
+		dev->caps.port_mask[i] = dev->caps.port_type[i];
+
 	if (dev->caps.uar_page_size * (dev->caps.num_uars -
 				       dev->caps.reserved_uars) >
 				       pci_resource_len(dev->pdev, 2)) {
@@ -504,18 +504,6 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		return -ENODEV;
 	}
 
-#if 0
-	mlx4_warn(dev, "sqp_demux:%d\n", dev->caps.sqp_demux);
-	mlx4_warn(dev, "num_uars:%d reserved_uars:%d uar region:0x%x bar2:0x%llx\n",
-		  dev->caps.num_uars, dev->caps.reserved_uars,
-		  dev->caps.uar_page_size * dev->caps.num_uars,
-		  pci_resource_len(dev->pdev, 2));
-	mlx4_warn(dev, "num_eqs:%d reserved_eqs:%d\n", dev->caps.num_eqs,
-		  dev->caps.reserved_eqs);
-	mlx4_warn(dev, "num_pds:%d reserved_pds:%d slave_pd_shift:%d pd_base:%d\n",
-		  dev->caps.num_pds, dev->caps.reserved_pds,
-		  dev->caps.slave_pd_shift, dev->caps.pd_base);
-#endif
 	return 0;
 }
 
@@ -810,9 +798,8 @@ static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
 	if (err)
 		goto err_srq;
 
-	num_eqs = (mlx4_is_master(dev)) ?
-		roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
-		dev->caps.num_eqs;
+	num_eqs = (mlx4_is_master(dev)) ? dev->phys_caps.num_phys_eqs :
+		  dev->caps.num_eqs;
 	err = mlx4_init_icm_table(dev, &priv->eq_table.cmpt_table,
 				  cmpt_base +
 				  ((u64) (MLX4_CMPT_TYPE_EQ *
@@ -874,9 +861,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 	}
 
 
-	num_eqs = (mlx4_is_master(dev)) ?
-		roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
-		dev->caps.num_eqs;
+	num_eqs = (mlx4_is_master(dev)) ? dev->phys_caps.num_phys_eqs :
+		   dev->caps.num_eqs;
 	err = mlx4_init_icm_table(dev, &priv->eq_table.table,
 				  init_hca->eqc_base, dev_cap->eqc_entry_sz,
 				  num_eqs, num_eqs, 0, 0);

drivers/net/ethernet/mellanox/mlx4/mlx4.h

@@ -1039,6 +1039,11 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev);
 void mlx4_free_resource_tracker(struct mlx4_dev *dev,
 				enum mlx4_res_tracker_free_type type);
 
+int mlx4_QUERY_FW_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
 int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			  struct mlx4_vhcr *vhcr,
 			  struct mlx4_cmd_mailbox *inbox,
@@ -1054,6 +1059,11 @@ int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			    struct mlx4_cmd_mailbox *inbox,
 			    struct mlx4_cmd_mailbox *outbox,
 			    struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
+			       struct mlx4_vhcr *vhcr,
+			       struct mlx4_cmd_mailbox *inbox,
+			       struct mlx4_cmd_mailbox *outbox,
+			       struct mlx4_cmd_info *cmd);
 int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			    struct mlx4_vhcr *vhcr,
 			    struct mlx4_cmd_mailbox *inbox,

drivers/net/ethernet/mellanox/mlx4/profile.c

@@ -126,7 +126,9 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	profile[MLX4_RES_AUXC].num    = request->num_qp;
 	profile[MLX4_RES_SRQ].num     = request->num_srq;
 	profile[MLX4_RES_CQ].num      = request->num_cq;
-	profile[MLX4_RES_EQ].num      = min_t(unsigned, dev_cap->max_eqs, MAX_MSIX);
+	profile[MLX4_RES_EQ].num      = mlx4_is_mfunc(dev) ?
+					dev->phys_caps.num_phys_eqs :
+					min_t(unsigned, dev_cap->max_eqs, MAX_MSIX);
 	profile[MLX4_RES_DMPT].num    = request->num_mpt;
 	profile[MLX4_RES_CMPT].num    = MLX4_NUM_CMPTS;
 	profile[MLX4_RES_MTT].num     = request->num_mtt * (1 << log_mtts_per_seg);
@@ -215,9 +217,10 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 			init_hca->log_num_cqs = profile[i].log_num;
 			break;
 		case MLX4_RES_EQ:
-			dev->caps.num_eqs     = profile[i].num;
+			dev->caps.num_eqs     = roundup_pow_of_two(min_t(unsigned, dev_cap->max_eqs,
+									 MAX_MSIX));
 			init_hca->eqc_base    = profile[i].start;
-			init_hca->log_num_eqs = profile[i].log_num;
+			init_hca->log_num_eqs = ilog2(dev->caps.num_eqs);
 			break;
 		case MLX4_RES_DMPT:
 			dev->caps.num_mpts	= profile[i].num;