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, 231 insertions, 0 deletions

diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c
new file mode 100644
index 00000000000..2346b38b983
--- /dev/null
+++ b/drivers/net/phy/bcm87xx.c
@@ -0,0 +1,231 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2011 - 2012 Cavium, Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/of.h>
+
+#define PHY_ID_BCM8706	0x0143bdc1
+#define PHY_ID_BCM8727	0x0143bff0
+
+#define BCM87XX_PMD_RX_SIGNAL_DETECT	(MII_ADDR_C45 | 0x1000a)
+#define BCM87XX_10GBASER_PCS_STATUS	(MII_ADDR_C45 | 0x30020)
+#define BCM87XX_XGXS_LANE_STATUS	(MII_ADDR_C45 | 0x40018)
+
+#define BCM87XX_LASI_CONTROL (MII_ADDR_C45 | 0x39002)
+#define BCM87XX_LASI_STATUS (MII_ADDR_C45 | 0x39005)
+
+#if IS_ENABLED(CONFIG_OF_MDIO)
+/* Set and/or override some configuration registers based on the
+ * broadcom,c45-reg-init property stored in the of_node for the phydev.
+ *
+ * broadcom,c45-reg-init = <devid reg mask value>,...;
+ *
+ * There may be one or more sets of <devid reg mask value>:
+ *
+ * devid: which sub-device to use.
+ * reg: the register.
+ * mask: if non-zero, ANDed with existing register value.
+ * value: ORed with the masked value and written to the regiser.
+ *
+ */
+static int bcm87xx_of_reg_init(struct phy_device *phydev)
+{
+	const __be32 *paddr;
+	const __be32 *paddr_end;
+	int len, ret;
+
+	if (!phydev->dev.of_node)
+		return 0;
+
+	paddr = of_get_property(phydev->dev.of_node,
+				"broadcom,c45-reg-init", &len);
+	if (!paddr)
+		return 0;
+
+	paddr_end = paddr + (len /= sizeof(*paddr));
+
+	ret = 0;
+
+	while (paddr + 3 < paddr_end) {
+		u16 devid	= be32_to_cpup(paddr++);
+		u16 reg		= be32_to_cpup(paddr++);
+		u16 mask	= be32_to_cpup(paddr++);
+		u16 val_bits	= be32_to_cpup(paddr++);
+		int val;
+		u32 regnum = MII_ADDR_C45 | (devid << 16) | reg;
+		val = 0;
+		if (mask) {
+			val = phy_read(phydev, regnum);
+			if (val < 0) {
+				ret = val;
+				goto err;
+			}
+			val &= mask;
+		}
+		val |= val_bits;
+
+		ret = phy_write(phydev, regnum, val);
+		if (ret < 0)
+			goto err;
+	}
+err:
+	return ret;
+}
+#else
+static int bcm87xx_of_reg_init(struct phy_device *phydev)
+{
+	return 0;
+}
+#endif /* CONFIG_OF_MDIO */
+
+static int bcm87xx_config_init(struct phy_device *phydev)
+{
+	phydev->supported = SUPPORTED_10000baseR_FEC;
+	phydev->advertising = ADVERTISED_10000baseR_FEC;
+	phydev->state = PHY_NOLINK;
+	phydev->autoneg = AUTONEG_DISABLE;
+
+	bcm87xx_of_reg_init(phydev);
+
+	return 0;
+}
+
+static int bcm87xx_config_aneg(struct phy_device *phydev)
+{
+	return -EINVAL;
+}
+
+static int bcm87xx_read_status(struct phy_device *phydev)
+{
+	int rx_signal_detect;
+	int pcs_status;
+	int xgxs_lane_status;
+
+	rx_signal_detect = phy_read(phydev, BCM87XX_PMD_RX_SIGNAL_DETECT);
+	if (rx_signal_detect < 0)
+		return rx_signal_detect;
+
+	if ((rx_signal_detect & 1) == 0)
+		goto no_link;
+
+	pcs_status = phy_read(phydev, BCM87XX_10GBASER_PCS_STATUS);
+	if (pcs_status < 0)
+		return pcs_status;
+
+	if ((pcs_status & 1) == 0)
+		goto no_link;
+
+	xgxs_lane_status = phy_read(phydev, BCM87XX_XGXS_LANE_STATUS);
+	if (xgxs_lane_status < 0)
+		return xgxs_lane_status;
+
+	if ((xgxs_lane_status & 0x1000) == 0)
+		goto no_link;
+
+	phydev->speed = 10000;
+	phydev->link = 1;
+	phydev->duplex = 1;
+	return 0;
+
+no_link:
+	phydev->link = 0;
+	return 0;
+}
+
+static int bcm87xx_config_intr(struct phy_device *phydev)
+{
+	int reg, err;
+
+	reg = phy_read(phydev, BCM87XX_LASI_CONTROL);
+
+	if (reg < 0)
+		return reg;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		reg |= 1;
+	else
+		reg &= ~1;
+
+	err = phy_write(phydev, BCM87XX_LASI_CONTROL, reg);
+	return err;
+}
+
+static int bcm87xx_did_interrupt(struct phy_device *phydev)
+{
+	int reg;
+
+	reg = phy_read(phydev, BCM87XX_LASI_STATUS);
+
+	if (reg < 0) {
+		dev_err(&phydev->dev,
+			"Error: Read of BCM87XX_LASI_STATUS failed: %d\n", reg);
+		return 0;
+	}
+	return (reg & 1) != 0;
+}
+
+static int bcm87xx_ack_interrupt(struct phy_device *phydev)
+{
+	/* Reading the LASI status clears it. */
+	bcm87xx_did_interrupt(phydev);
+	return 0;
+}
+
+static int bcm8706_match_phy_device(struct phy_device *phydev)
+{
+	return phydev->c45_ids.device_ids[4] == PHY_ID_BCM8706;
+}
+
+static int bcm8727_match_phy_device(struct phy_device *phydev)
+{
+	return phydev->c45_ids.device_ids[4] == PHY_ID_BCM8727;
+}
+
+static struct phy_driver bcm87xx_driver[] = {
+{
+	.phy_id		= PHY_ID_BCM8706,
+	.phy_id_mask	= 0xffffffff,
+	.name		= "Broadcom BCM8706",
+	.flags		= PHY_HAS_INTERRUPT,
+	.config_init	= bcm87xx_config_init,
+	.config_aneg	= bcm87xx_config_aneg,
+	.read_status	= bcm87xx_read_status,
+	.ack_interrupt	= bcm87xx_ack_interrupt,
+	.config_intr	= bcm87xx_config_intr,
+	.did_interrupt	= bcm87xx_did_interrupt,
+	.match_phy_device = bcm8706_match_phy_device,
+	.driver		= { .owner = THIS_MODULE },
+}, {
+	.phy_id		= PHY_ID_BCM8727,
+	.phy_id_mask	= 0xffffffff,
+	.name		= "Broadcom BCM8727",
+	.flags		= PHY_HAS_INTERRUPT,
+	.config_init	= bcm87xx_config_init,
+	.config_aneg	= bcm87xx_config_aneg,
+	.read_status	= bcm87xx_read_status,
+	.ack_interrupt	= bcm87xx_ack_interrupt,
+	.config_intr	= bcm87xx_config_intr,
+	.did_interrupt	= bcm87xx_did_interrupt,
+	.match_phy_device = bcm8727_match_phy_device,
+	.driver		= { .owner = THIS_MODULE },
+} };
+
+static int __init bcm87xx_init(void)
+{
+	return phy_drivers_register(bcm87xx_driver,
+		ARRAY_SIZE(bcm87xx_driver));
+}
+module_init(bcm87xx_init);
+
+static void __exit bcm87xx_exit(void)
+{
+	phy_drivers_unregister(bcm87xx_driver,
+		ARRAY_SIZE(bcm87xx_driver));
+}
+module_exit(bcm87xx_exit);