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
  ...

1 files changed, 170 insertions, 26 deletions

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ea3003edde18..f6b04c1a3672 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -133,6 +133,12 @@ static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
 				      NETIF_MSG_LINK | NETIF_MSG_IFUP |
 				      NETIF_MSG_IFDOWN | NETIF_MSG_TIMER);
 
+#define STMMAC_DEFAULT_LPI_TIMER	1000
+static int eee_timer = STMMAC_DEFAULT_LPI_TIMER;
+module_param(eee_timer, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec");
+#define STMMAC_LPI_TIMER(x) (jiffies + msecs_to_jiffies(x))
+
 static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
 
 #ifdef CONFIG_STMMAC_DEBUG_FS
@@ -161,6 +167,8 @@ static void stmmac_verify_args(void)
 		flow_ctrl = FLOW_OFF;
 	if (unlikely((pause < 0) || (pause > 0xffff)))
 		pause = PAUSE_TIME;
+	if (eee_timer < 0)
+		eee_timer = STMMAC_DEFAULT_LPI_TIMER;
 }
 
 static void stmmac_clk_csr_set(struct stmmac_priv *priv)
@@ -229,6 +237,85 @@ static inline void stmmac_hw_fix_mac_speed(struct stmmac_priv *priv)
 					  phydev->speed);
 }
 
+static void stmmac_enable_eee_mode(struct stmmac_priv *priv)
+{
+	/* Check and enter in LPI mode */
+	if ((priv->dirty_tx == priv->cur_tx) &&
+	    (priv->tx_path_in_lpi_mode == false))
+		priv->hw->mac->set_eee_mode(priv->ioaddr);
+}
+
+void stmmac_disable_eee_mode(struct stmmac_priv *priv)
+{
+	/* Exit and disable EEE in case of we are are in LPI state. */
+	priv->hw->mac->reset_eee_mode(priv->ioaddr);
+	del_timer_sync(&priv->eee_ctrl_timer);
+	priv->tx_path_in_lpi_mode = false;
+}
+
+/**
+ * stmmac_eee_ctrl_timer
+ * @arg : data hook
+ * Description:
+ *  If there is no data transfer and if we are not in LPI state,
+ *  then MAC Transmitter can be moved to LPI state.
+ */
+static void stmmac_eee_ctrl_timer(unsigned long arg)
+{
+	struct stmmac_priv *priv = (struct stmmac_priv *)arg;
+
+	stmmac_enable_eee_mode(priv);
+	mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_TIMER(eee_timer));
+}
+
+/**
+ * stmmac_eee_init
+ * @priv: private device pointer
+ * Description:
+ *  If the EEE support has been enabled while configuring the driver,
+ *  if the GMAC actually supports the EEE (from the HW cap reg) and the
+ *  phy can also manage EEE, so enable the LPI state and start the timer
+ *  to verify if the tx path can enter in LPI state.
+ */
+bool stmmac_eee_init(struct stmmac_priv *priv)
+{
+	bool ret = false;
+
+	/* MAC core supports the EEE feature. */
+	if (priv->dma_cap.eee) {
+		/* Check if the PHY supports EEE */
+		if (phy_init_eee(priv->phydev, 1))
+			goto out;
+
+		priv->eee_active = 1;
+		init_timer(&priv->eee_ctrl_timer);
+		priv->eee_ctrl_timer.function = stmmac_eee_ctrl_timer;
+		priv->eee_ctrl_timer.data = (unsigned long)priv;
+		priv->eee_ctrl_timer.expires = STMMAC_LPI_TIMER(eee_timer);
+		add_timer(&priv->eee_ctrl_timer);
+
+		priv->hw->mac->set_eee_timer(priv->ioaddr,
+					     STMMAC_DEFAULT_LIT_LS_TIMER,
+					     priv->tx_lpi_timer);
+
+		pr_info("stmmac: Energy-Efficient Ethernet initialized\n");
+
+		ret = true;
+	}
+out:
+	return ret;
+}
+
+static void stmmac_eee_adjust(struct stmmac_priv *priv)
+{
+	/* When the EEE has been already initialised we have to
+	 * modify the PLS bit in the LPI ctrl & status reg according
+	 * to the PHY link status. For this reason.
+	 */
+	if (priv->eee_enabled)
+		priv->hw->mac->set_eee_pls(priv->ioaddr, priv->phydev->link);
+}
+
 /**
  * stmmac_adjust_link
  * @dev: net device structure
@@ -249,6 +336,7 @@ static void stmmac_adjust_link(struct net_device *dev)
 	    phydev->addr, phydev->link);
 
 	spin_lock_irqsave(&priv->lock, flags);
+
 	if (phydev->link) {
 		u32 ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
 
@@ -315,6 +403,8 @@ static void stmmac_adjust_link(struct net_device *dev)
 	if (new_state && netif_msg_link(priv))
 		phy_print_status(phydev);
 
+	stmmac_eee_adjust(priv);
+
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	DBG(probe, DEBUG, "stmmac_adjust_link: exiting\n");
@@ -332,7 +422,7 @@ static int stmmac_init_phy(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	struct phy_device *phydev;
-	char phy_id[MII_BUS_ID_SIZE + 3];
+	char phy_id_fmt[MII_BUS_ID_SIZE + 3];
 	char bus_id[MII_BUS_ID_SIZE];
 	int interface = priv->plat->interface;
 	priv->oldlink = 0;
@@ -346,11 +436,12 @@ static int stmmac_init_phy(struct net_device *dev)
 		snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x",
 				priv->plat->bus_id);
 
-	snprintf(phy_id, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
+	snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
 		 priv->plat->phy_addr);
-	pr_debug("stmmac_init_phy:  trying to attach to %s\n", phy_id);
+	pr_debug("stmmac_init_phy:  trying to attach to %s\n", phy_id_fmt);
 
-	phydev = phy_connect(dev, phy_id, &stmmac_adjust_link, 0, interface);
+	phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link, 0,
+			     interface);
 
 	if (IS_ERR(phydev)) {
 		pr_err("%s: Could not attach to PHY\n", dev->name);
@@ -677,7 +768,7 @@ static void stmmac_tx(struct stmmac_priv *priv)
 
 		priv->hw->desc->release_tx_desc(p);
 
-		entry = (++priv->dirty_tx) % txsize;
+		priv->dirty_tx++;
 	}
 	if (unlikely(netif_queue_stopped(priv->dev) &&
 		     stmmac_tx_avail(priv) > STMMAC_TX_THRESH(priv))) {
@@ -689,6 +780,11 @@ static void stmmac_tx(struct stmmac_priv *priv)
 		}
 		netif_tx_unlock(priv->dev);
 	}
+
+	if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
+		stmmac_enable_eee_mode(priv);
+		mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_TIMER(eee_timer));
+	}
 	spin_unlock(&priv->tx_lock);
 }
 
@@ -1027,6 +1123,17 @@ static int stmmac_open(struct net_device *dev)
 		}
 	}
 
+	/* Request the IRQ lines */
+	if (priv->lpi_irq != -ENXIO) {
+		ret = request_irq(priv->lpi_irq, stmmac_interrupt, IRQF_SHARED,
+				  dev->name, dev);
+		if (unlikely(ret < 0)) {
+			pr_err("%s: ERROR: allocating the LPI IRQ %d (%d)\n",
+			       __func__, priv->lpi_irq, ret);
+			goto open_error_lpiirq;
+		}
+	}
+
 	/* Enable the MAC Rx/Tx */
 	stmmac_set_mac(priv->ioaddr, true);
 
@@ -1062,12 +1169,19 @@ static int stmmac_open(struct net_device *dev)
 	if (priv->phydev)
 		phy_start(priv->phydev);
 
+	priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS_TIMER;
+	priv->eee_enabled = stmmac_eee_init(priv);
+
 	napi_enable(&priv->napi);
 	skb_queue_head_init(&priv->rx_recycle);
 	netif_start_queue(dev);
 
 	return 0;
 
+open_error_lpiirq:
+	if (priv->wol_irq != dev->irq)
+		free_irq(priv->wol_irq, dev);
+
 open_error_wolirq:
 	free_irq(dev->irq, dev);
 
@@ -1093,6 +1207,9 @@ static int stmmac_release(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
+	if (priv->eee_enabled)
+		del_timer_sync(&priv->eee_ctrl_timer);
+
 	/* Stop and disconnect the PHY */
 	if (priv->phydev) {
 		phy_stop(priv->phydev);
@@ -1115,6 +1232,8 @@ static int stmmac_release(struct net_device *dev)
 	free_irq(dev->irq, dev);
 	if (priv->wol_irq != dev->irq)
 		free_irq(priv->wol_irq, dev);
+	if (priv->lpi_irq != -ENXIO)
+		free_irq(priv->lpi_irq, dev);
 
 	/* Stop TX/RX DMA and clear the descriptors */
 	priv->hw->dma->stop_tx(priv->ioaddr);
@@ -1164,6 +1283,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	spin_lock(&priv->tx_lock);
 
+	if (priv->tx_path_in_lpi_mode)
+		stmmac_disable_eee_mode(priv);
+
 	entry = priv->cur_tx % txsize;
 
 #ifdef STMMAC_XMIT_DEBUG
@@ -1311,7 +1433,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 		display_ring(priv->dma_rx, rxsize);
 	}
 #endif
-	count = 0;
 	while (!priv->hw->desc->get_rx_owner(p)) {
 		int status;
 
@@ -1544,10 +1665,37 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 		return IRQ_NONE;
 	}
 
-	if (priv->plat->has_gmac)
-		/* To handle GMAC own interrupts */
-		priv->hw->mac->host_irq_status((void __iomem *) dev->base_addr);
+	/* To handle GMAC own interrupts */
+	if (priv->plat->has_gmac) {
+		int status = priv->hw->mac->host_irq_status((void __iomem *)
+							    dev->base_addr);
+		if (unlikely(status)) {
+			if (status & core_mmc_tx_irq)
+				priv->xstats.mmc_tx_irq_n++;
+			if (status & core_mmc_rx_irq)
+				priv->xstats.mmc_rx_irq_n++;
+			if (status & core_mmc_rx_csum_offload_irq)
+				priv->xstats.mmc_rx_csum_offload_irq_n++;
+			if (status & core_irq_receive_pmt_irq)
+				priv->xstats.irq_receive_pmt_irq_n++;
+
+			/* For LPI we need to save the tx status */
+			if (status & core_irq_tx_path_in_lpi_mode) {
+				priv->xstats.irq_tx_path_in_lpi_mode_n++;
+				priv->tx_path_in_lpi_mode = true;
+			}
+			if (status & core_irq_tx_path_exit_lpi_mode) {
+				priv->xstats.irq_tx_path_exit_lpi_mode_n++;
+				priv->tx_path_in_lpi_mode = false;
+			}
+			if (status & core_irq_rx_path_in_lpi_mode)
+				priv->xstats.irq_rx_path_in_lpi_mode_n++;
+			if (status & core_irq_rx_path_exit_lpi_mode)
+				priv->xstats.irq_rx_path_exit_lpi_mode_n++;
+		}
+	}
 
+	/* To handle DMA interrupts */
 	stmmac_dma_interrupt(priv);
 
 	return IRQ_HANDLED;
@@ -2133,42 +2281,38 @@ static int __init stmmac_cmdline_opt(char *str)
 		return -EINVAL;
 	while ((opt = strsep(&str, ",")) != NULL) {
 		if (!strncmp(opt, "debug:", 6)) {
-			if (strict_strtoul(opt + 6, 0, (unsigned long *)&debug))
+			if (kstrtoint(opt + 6, 0, &debug))
 				goto err;
 		} else if (!strncmp(opt, "phyaddr:", 8)) {
-			if (strict_strtoul(opt + 8, 0,
-					   (unsigned long *)&phyaddr))
+			if (kstrtoint(opt + 8, 0, &phyaddr))
 				goto err;
 		} else if (!strncmp(opt, "dma_txsize:", 11)) {
-			if (strict_strtoul(opt + 11, 0,
-					   (unsigned long *)&dma_txsize))
+			if (kstrtoint(opt + 11, 0, &dma_txsize))
 				goto err;
 		} else if (!strncmp(opt, "dma_rxsize:", 11)) {
-			if (strict_strtoul(opt + 11, 0,
-					   (unsigned long *)&dma_rxsize))
+			if (kstrtoint(opt + 11, 0, &dma_rxsize))
 				goto err;
 		} else if (!strncmp(opt, "buf_sz:", 7)) {
-			if (strict_strtoul(opt + 7, 0,
-					   (unsigned long *)&buf_sz))
+			if (kstrtoint(opt + 7, 0, &buf_sz))
 				goto err;
 		} else if (!strncmp(opt, "tc:", 3)) {
-			if (strict_strtoul(opt + 3, 0, (unsigned long *)&tc))
+			if (kstrtoint(opt + 3, 0, &tc))
 				goto err;
 		} else if (!strncmp(opt, "watchdog:", 9)) {
-			if (strict_strtoul(opt + 9, 0,
-					   (unsigned long *)&watchdog))
+			if (kstrtoint(opt + 9, 0, &watchdog))
 				goto err;
 		} else if (!strncmp(opt, "flow_ctrl:", 10)) {
-			if (strict_strtoul(opt + 10, 0,
-					   (unsigned long *)&flow_ctrl))
+			if (kstrtoint(opt + 10, 0, &flow_ctrl))
 				goto err;
 		} else if (!strncmp(opt, "pause:", 6)) {
-			if (strict_strtoul(opt + 6, 0, (unsigned long *)&pause))
+			if (kstrtoint(opt + 6, 0, &pause))
+				goto err;
+		} else if (!strncmp(opt, "eee_timer:", 6)) {
+			if (kstrtoint(opt + 10, 0, &eee_timer))
 				goto err;
 #ifdef CONFIG_STMMAC_TIMER
 		} else if (!strncmp(opt, "tmrate:", 7)) {
-			if (strict_strtoul(opt + 7, 0,
-					   (unsigned long *)&tmrate))
+			if (kstrtoint(opt + 7, 0, &tmrate))
 				goto err;
 #endif
 		}