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

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

5 files changed, 204 insertions, 50 deletions

diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 35d1e4f2c92..10efcd88dca 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -117,6 +117,7 @@
 
 /* TX Rate Limit Registers */
 #define E1000_RTTDQSEL	0x3604	/* Tx Desc Plane Queue Select - WO */
+#define E1000_RTTBCNRM	0x3690	/* Tx BCN Rate-scheduler MMW */
 #define E1000_RTTBCNRC	0x36B0	/* Tx BCN Rate-Scheduler Config - WO */
 
 /* Split and Replication RX Control - RW */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index ae6d3f393a5..9e572dd29ab 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -65,19 +65,30 @@ struct igb_adapter;
 #define MAX_Q_VECTORS                      8
 
 /* Transmit and receive queues */
-#define IGB_MAX_RX_QUEUES		((adapter->vfs_allocated_count ? 2 : \
-					(hw->mac.type > e1000_82575 ? 8 : 4)))
-#define IGB_MAX_RX_QUEUES_I210             4
+#define IGB_MAX_RX_QUEUES                  8
+#define IGB_MAX_RX_QUEUES_82575            4
 #define IGB_MAX_RX_QUEUES_I211             2
-#define IGB_MAX_TX_QUEUES                  16
-#define IGB_MAX_TX_QUEUES_I210             4
-#define IGB_MAX_TX_QUEUES_I211             2
+#define IGB_MAX_TX_QUEUES                  8
 #define IGB_MAX_VF_MC_ENTRIES              30
 #define IGB_MAX_VF_FUNCTIONS               8
 #define IGB_MAX_VFTA_ENTRIES               128
 #define IGB_82576_VF_DEV_ID                0x10CA
 #define IGB_I350_VF_DEV_ID                 0x1520
 
+/* NVM version defines */
+#define IGB_MAJOR_MASK			0xF000
+#define IGB_MINOR_MASK			0x0FF0
+#define IGB_BUILD_MASK			0x000F
+#define IGB_COMB_VER_MASK		0x00FF
+#define IGB_MAJOR_SHIFT			12
+#define IGB_MINOR_SHIFT			4
+#define IGB_COMB_VER_SHFT		8
+#define IGB_NVM_VER_INVALID		0xFFFF
+#define IGB_ETRACK_SHIFT		16
+#define NVM_ETRACK_WORD			0x0042
+#define NVM_COMB_VER_OFF		0x0083
+#define NVM_COMB_VER_PTR		0x003d
+
 struct vf_data_storage {
 	unsigned char vf_mac_addresses[ETH_ALEN];
 	u16 vf_mc_hashes[IGB_MAX_VF_MC_ENTRIES];
@@ -371,6 +382,7 @@ struct igb_adapter {
 	spinlock_t tmreg_lock;
 	struct cyclecounter cc;
 	struct timecounter tc;
+	char fw_version[32];
 };
 
 #define IGB_FLAG_HAS_MSI           (1 << 0)
@@ -420,6 +432,7 @@ extern void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *);
 extern bool igb_has_link(struct igb_adapter *adapter);
 extern void igb_set_ethtool_ops(struct net_device *);
 extern void igb_power_up_link(struct igb_adapter *);
+extern void igb_set_fw_version(struct igb_adapter *);
 #ifdef CONFIG_IGB_PTP
 extern void igb_ptp_init(struct igb_adapter *adapter);
 extern void igb_ptp_remove(struct igb_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 812d4f963bd..a19c84cad0e 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -710,6 +710,7 @@ static int igb_set_eeprom(struct net_device *netdev,
 	if ((ret_val == 0) && ((first_word <= NVM_CHECKSUM_REG)))
 		hw->nvm.ops.update(hw);
 
+	igb_set_fw_version(adapter);
 	kfree(eeprom_buff);
 	return ret_val;
 }
@@ -718,20 +719,16 @@ static void igb_get_drvinfo(struct net_device *netdev,
 			    struct ethtool_drvinfo *drvinfo)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
-	u16 eeprom_data;
 
 	strlcpy(drvinfo->driver,  igb_driver_name, sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, igb_driver_version, sizeof(drvinfo->version));
 
-	/* EEPROM image version # is reported as firmware version # for
-	 * 82575 controllers */
-	adapter->hw.nvm.ops.read(&adapter->hw, 5, 1, &eeprom_data);
-	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
-		"%d.%d-%d",
-		(eeprom_data & 0xF000) >> 12,
-		(eeprom_data & 0x0FF0) >> 4,
-		eeprom_data & 0x000F);
-
+	/*
+	 * EEPROM image version # is reported as firmware version # for
+	 * 82575 controllers
+	 */
+	strlcpy(drvinfo->fw_version, adapter->fw_version,
+		sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
 		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = IGB_STATS_LEN;
@@ -2271,6 +2268,38 @@ static void igb_ethtool_complete(struct net_device *netdev)
 	pm_runtime_put(&adapter->pdev->dev);
 }
 
+#ifdef CONFIG_IGB_PTP
+static int igb_ethtool_get_ts_info(struct net_device *dev,
+				   struct ethtool_ts_info *info)
+{
+	struct igb_adapter *adapter = netdev_priv(dev);
+
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_HARDWARE |
+		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	if (adapter->ptp_clock)
+		info->phc_index = ptp_clock_index(adapter->ptp_clock);
+	else
+		info->phc_index = -1;
+
+	info->tx_types =
+		(1 << HWTSTAMP_TX_OFF) |
+		(1 << HWTSTAMP_TX_ON);
+
+	info->rx_filters =
+		(1 << HWTSTAMP_FILTER_NONE) |
+		(1 << HWTSTAMP_FILTER_ALL) |
+		(1 << HWTSTAMP_FILTER_SOME) |
+		(1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
+
+	return 0;
+}
+
+#endif
 static const struct ethtool_ops igb_ethtool_ops = {
 	.get_settings           = igb_get_settings,
 	.set_settings           = igb_set_settings,
@@ -2299,6 +2328,9 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.set_coalesce           = igb_set_coalesce,
 	.begin			= igb_ethtool_begin,
 	.complete		= igb_ethtool_complete,
+#ifdef CONFIG_IGB_PTP
+	.get_ts_info		= igb_ethtool_get_ts_info,
+#endif
 };
 
 void igb_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index dd3bfe8cd36..1050411e7ca 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -59,9 +59,9 @@
 #endif
 #include "igb.h"
 
-#define MAJ 3
-#define MIN 4
-#define BUILD 7
+#define MAJ 4
+#define MIN 0
+#define BUILD 1
 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
 __stringify(BUILD) "-k"
 char igb_driver_name[] = "igb";
@@ -1048,11 +1048,6 @@ static int igb_set_interrupt_capability(struct igb_adapter *adapter)
 	if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS))
 		numvecs += adapter->num_tx_queues;
 
-	/* i210 and i211 can only have 4 MSIX vectors for rx/tx queues. */
-	if ((adapter->hw.mac.type == e1000_i210)
-		|| (adapter->hw.mac.type == e1000_i211))
-		numvecs = 4;
-
 	/* store the number of vectors reserved for queues */
 	adapter->num_q_vectors = numvecs;
 
@@ -1505,11 +1500,12 @@ static void igb_configure(struct igb_adapter *adapter)
  **/
 void igb_power_up_link(struct igb_adapter *adapter)
 {
+	igb_reset_phy(&adapter->hw);
+
 	if (adapter->hw.phy.media_type == e1000_media_type_copper)
 		igb_power_up_phy_copper(&adapter->hw);
 	else
 		igb_power_up_serdes_link_82575(&adapter->hw);
-	igb_reset_phy(&adapter->hw);
 }
 
 /**
@@ -1821,6 +1817,69 @@ static const struct net_device_ops igb_netdev_ops = {
 };
 
 /**
+ * igb_set_fw_version - Configure version string for ethtool
+ * @adapter: adapter struct
+ *
+ **/
+void igb_set_fw_version(struct igb_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	u16 eeprom_verh, eeprom_verl, comb_verh, comb_verl, comb_offset;
+	u16 major, build, patch, fw_version;
+	u32 etrack_id;
+
+	hw->nvm.ops.read(hw, 5, 1, &fw_version);
+	if (adapter->hw.mac.type != e1000_i211) {
+		hw->nvm.ops.read(hw, NVM_ETRACK_WORD, 1, &eeprom_verh);
+		hw->nvm.ops.read(hw, (NVM_ETRACK_WORD + 1), 1, &eeprom_verl);
+		etrack_id = (eeprom_verh << IGB_ETRACK_SHIFT) | eeprom_verl;
+
+		/* combo image version needs to be found */
+		hw->nvm.ops.read(hw, NVM_COMB_VER_PTR, 1, &comb_offset);
+		if ((comb_offset != 0x0) &&
+		    (comb_offset != IGB_NVM_VER_INVALID)) {
+			hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset
+					 + 1), 1, &comb_verh);
+			hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset),
+					 1, &comb_verl);
+
+			/* Only display Option Rom if it exists and is valid */
+			if ((comb_verh && comb_verl) &&
+			    ((comb_verh != IGB_NVM_VER_INVALID) &&
+			     (comb_verl != IGB_NVM_VER_INVALID))) {
+				major = comb_verl >> IGB_COMB_VER_SHFT;
+				build = (comb_verl << IGB_COMB_VER_SHFT) |
+					(comb_verh >> IGB_COMB_VER_SHFT);
+				patch = comb_verh & IGB_COMB_VER_MASK;
+				snprintf(adapter->fw_version,
+					 sizeof(adapter->fw_version),
+					 "%d.%d%d, 0x%08x, %d.%d.%d",
+					 (fw_version & IGB_MAJOR_MASK) >>
+					 IGB_MAJOR_SHIFT,
+					 (fw_version & IGB_MINOR_MASK) >>
+					 IGB_MINOR_SHIFT,
+					 (fw_version & IGB_BUILD_MASK),
+					 etrack_id, major, build, patch);
+				goto out;
+			}
+		}
+		snprintf(adapter->fw_version, sizeof(adapter->fw_version),
+			 "%d.%d%d, 0x%08x",
+			 (fw_version & IGB_MAJOR_MASK) >> IGB_MAJOR_SHIFT,
+			 (fw_version & IGB_MINOR_MASK) >> IGB_MINOR_SHIFT,
+			 (fw_version & IGB_BUILD_MASK), etrack_id);
+	} else {
+		snprintf(adapter->fw_version, sizeof(adapter->fw_version),
+			 "%d.%d%d",
+			 (fw_version & IGB_MAJOR_MASK) >> IGB_MAJOR_SHIFT,
+			 (fw_version & IGB_MINOR_MASK) >> IGB_MINOR_SHIFT,
+			 (fw_version & IGB_BUILD_MASK));
+	}
+out:
+	return;
+}
+
+/**
  * igb_probe - Device Initialization Routine
  * @pdev: PCI device information struct
  * @ent: entry in igb_pci_tbl
@@ -2030,6 +2089,9 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 		goto err_eeprom;
 	}
 
+	/* get firmware version for ethtool -i */
+	igb_set_fw_version(adapter);
+
 	setup_timer(&adapter->watchdog_timer, igb_watchdog,
 	            (unsigned long) adapter);
 	setup_timer(&adapter->phy_info_timer, igb_update_phy_info,
@@ -2338,6 +2400,7 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
 	struct e1000_hw *hw = &adapter->hw;
 	struct net_device *netdev = adapter->netdev;
 	struct pci_dev *pdev = adapter->pdev;
+	u32 max_rss_queues;
 
 	pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
 
@@ -2370,40 +2433,69 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
 		} else
 			adapter->vfs_allocated_count = max_vfs;
 		break;
-	case e1000_i210:
-	case e1000_i211:
-		adapter->vfs_allocated_count = 0;
-		break;
 	default:
 		break;
 	}
 #endif /* CONFIG_PCI_IOV */
+
+	/* Determine the maximum number of RSS queues supported. */
 	switch (hw->mac.type) {
+	case e1000_i211:
+		max_rss_queues = IGB_MAX_RX_QUEUES_I211;
+		break;
+	case e1000_82575:
 	case e1000_i210:
-		adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES_I210,
-			num_online_cpus());
+		max_rss_queues = IGB_MAX_RX_QUEUES_82575;
+		break;
+	case e1000_i350:
+		/* I350 cannot do RSS and SR-IOV at the same time */
+		if (!!adapter->vfs_allocated_count) {
+			max_rss_queues = 1;
+			break;
+		}
+		/* fall through */
+	case e1000_82576:
+		if (!!adapter->vfs_allocated_count) {
+			max_rss_queues = 2;
+			break;
+		}
+		/* fall through */
+	case e1000_82580:
+	default:
+		max_rss_queues = IGB_MAX_RX_QUEUES;
 		break;
+	}
+
+	adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus());
+
+	/* Determine if we need to pair queues. */
+	switch (hw->mac.type) {
+	case e1000_82575:
 	case e1000_i211:
-		adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES_I211,
-			num_online_cpus());
+		/* Device supports enough interrupts without queue pairing. */
 		break;
+	case e1000_82576:
+		/*
+		 * If VFs are going to be allocated with RSS queues then we
+		 * should pair the queues in order to conserve interrupts due
+		 * to limited supply.
+		 */
+		if ((adapter->rss_queues > 1) &&
+		    (adapter->vfs_allocated_count > 6))
+			adapter->flags |= IGB_FLAG_QUEUE_PAIRS;
+		/* fall through */
+	case e1000_82580:
+	case e1000_i350:
+	case e1000_i210:
 	default:
-		adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES,
-		num_online_cpus());
+		/*
+		 * If rss_queues > half of max_rss_queues, pair the queues in
+		 * order to conserve interrupts due to limited supply.
+		 */
+		if (adapter->rss_queues > (max_rss_queues / 2))
+			adapter->flags |= IGB_FLAG_QUEUE_PAIRS;
 		break;
 	}
-	/* i350 cannot do RSS and SR-IOV at the same time */
-	if (hw->mac.type == e1000_i350 && adapter->vfs_allocated_count)
-		adapter->rss_queues = 1;
-
-	/*
-	 * if rss_queues > 4 or vfs are going to be allocated with rss_queues
-	 * then we should combine the queues into a queue pair in order to
-	 * conserve interrupts due to limited supply
-	 */
-	if ((adapter->rss_queues > 4) ||
-	    ((adapter->rss_queues > 1) && (adapter->vfs_allocated_count > 6)))
-		adapter->flags |= IGB_FLAG_QUEUE_PAIRS;
 
 	/* Setup and initialize a copy of the hw vlan table array */
 	adapter->shadow_vfta = kzalloc(sizeof(u32) *
@@ -4917,7 +5009,7 @@ static int igb_vf_configure(struct igb_adapter *adapter, int vf)
 	unsigned int device_id;
 	u16 thisvf_devfn;
 
-	random_ether_addr(mac_addr);
+	eth_random_addr(mac_addr);
 	igb_set_vf_mac(adapter, vf, mac_addr);
 
 	switch (adapter->hw.mac.type) {
@@ -5326,7 +5418,7 @@ static void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf)
 
 	/* generate a new mac address as we were hotplug removed/added */
 	if (!(adapter->vf_data[vf].flags & IGB_VF_FLAG_PF_SET_MAC))
-		random_ether_addr(vf_mac);
+		eth_random_addr(vf_mac);
 
 	/* process remaining reset events */
 	igb_vf_reset(adapter, vf);
@@ -5686,6 +5778,7 @@ static void igb_tx_hwtstamp(struct igb_q_vector *q_vector,
 /**
  * igb_clean_tx_irq - Reclaim resources after transmit completes
  * @q_vector: pointer to q_vector containing needed info
+ *
  * returns true if ring is completely cleaned
  **/
 static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
@@ -6997,6 +7090,11 @@ static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate,
 	}
 
 	wr32(E1000_RTTDQSEL, vf); /* vf X uses queue X */
+	/*
+	 * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM
+	 * register. MMW_SIZE=0x014 if 9728-byte jumbo is supported.
+	 */
+	wr32(E1000_RTTBCNRM, 0x14);
 	wr32(E1000_RTTBCNRC, bcnrc_val);
 }
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index d5ee7fa5072..c846ea9131a 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -330,7 +330,17 @@ void igb_ptp_init(struct igb_adapter *adapter)
 
 void igb_ptp_remove(struct igb_adapter *adapter)
 {
-	cancel_delayed_work_sync(&adapter->overflow_work);
+	switch (adapter->hw.mac.type) {
+	case e1000_i211:
+	case e1000_i210:
+	case e1000_i350:
+	case e1000_82580:
+	case e1000_82576:
+		cancel_delayed_work_sync(&adapter->overflow_work);
+		break;
+	default:
+		return;
+	}
 
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);