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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 327 insertions, 11 deletions

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 9d56515f4c4d..6f946fedbb77 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -21,10 +21,13 @@
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
+#include <linux/of_net.h>
 #include <net/dsa.h>
 #include <linux/ethtool.h>
 #include <linux/if_bridge.h>
 #include <linux/brcmphy.h>
+#include <linux/etherdevice.h>
+#include <net/switchdev.h>
 
 #include "bcm_sf2.h"
 #include "bcm_sf2_regs.h"
@@ -264,6 +267,50 @@ static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable)
 	}
 }
 
+static inline void bcm_sf2_port_intr_enable(struct bcm_sf2_priv *priv,
+					    int port)
+{
+	unsigned int off;
+
+	switch (port) {
+	case 7:
+		off = P7_IRQ_OFF;
+		break;
+	case 0:
+		/* Port 0 interrupts are located on the first bank */
+		intrl2_0_mask_clear(priv, P_IRQ_MASK(P0_IRQ_OFF));
+		return;
+	default:
+		off = P_IRQ_OFF(port);
+		break;
+	}
+
+	intrl2_1_mask_clear(priv, P_IRQ_MASK(off));
+}
+
+static inline void bcm_sf2_port_intr_disable(struct bcm_sf2_priv *priv,
+					     int port)
+{
+	unsigned int off;
+
+	switch (port) {
+	case 7:
+		off = P7_IRQ_OFF;
+		break;
+	case 0:
+		/* Port 0 interrupts are located on the first bank */
+		intrl2_0_mask_set(priv, P_IRQ_MASK(P0_IRQ_OFF));
+		intrl2_0_writel(priv, P_IRQ_MASK(P0_IRQ_OFF), INTRL2_CPU_CLEAR);
+		return;
+	default:
+		off = P_IRQ_OFF(port);
+		break;
+	}
+
+	intrl2_1_mask_set(priv, P_IRQ_MASK(off));
+	intrl2_1_writel(priv, P_IRQ_MASK(off), INTRL2_CPU_CLEAR);
+}
+
 static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 			      struct phy_device *phy)
 {
@@ -280,7 +327,7 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 	core_writel(priv, 0, CORE_G_PCTL_PORT(port));
 
 	/* Re-enable the GPHY and re-apply workarounds */
-	if (port == 0 && priv->hw_params.num_gphy == 1) {
+	if (priv->int_phy_mask & 1 << port && priv->hw_params.num_gphy == 1) {
 		bcm_sf2_gphy_enable_set(ds, true);
 		if (phy) {
 			/* if phy_stop() has been called before, phy
@@ -297,9 +344,9 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 		}
 	}
 
-	/* Enable port 7 interrupts to get notified */
-	if (port == 7)
-		intrl2_1_mask_clear(priv, P_IRQ_MASK(P7_IRQ_OFF));
+	/* Enable MoCA port interrupts to get notified */
+	if (port == priv->moca_port)
+		bcm_sf2_port_intr_enable(priv, port);
 
 	/* Set this port, and only this one to be in the default VLAN,
 	 * if member of a bridge, restore its membership prior to
@@ -329,12 +376,10 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
 	if (priv->wol_ports_mask & (1 << port))
 		return;
 
-	if (port == 7) {
-		intrl2_1_mask_set(priv, P_IRQ_MASK(P7_IRQ_OFF));
-		intrl2_1_writel(priv, P_IRQ_MASK(P7_IRQ_OFF), INTRL2_CPU_CLEAR);
-	}
+	if (port == priv->moca_port)
+		bcm_sf2_port_intr_disable(priv, port);
 
-	if (port == 0 && priv->hw_params.num_gphy == 1)
+	if (priv->int_phy_mask & 1 << port && priv->hw_params.num_gphy == 1)
 		bcm_sf2_gphy_enable_set(ds, false);
 
 	if (dsa_is_cpu_port(ds, port))
@@ -555,6 +600,236 @@ static int bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port,
 	return 0;
 }
 
+/* Address Resolution Logic routines */
+static int bcm_sf2_arl_op_wait(struct bcm_sf2_priv *priv)
+{
+	unsigned int timeout = 10;
+	u32 reg;
+
+	do {
+		reg = core_readl(priv, CORE_ARLA_RWCTL);
+		if (!(reg & ARL_STRTDN))
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+static int bcm_sf2_arl_rw_op(struct bcm_sf2_priv *priv, unsigned int op)
+{
+	u32 cmd;
+
+	if (op > ARL_RW)
+		return -EINVAL;
+
+	cmd = core_readl(priv, CORE_ARLA_RWCTL);
+	cmd &= ~IVL_SVL_SELECT;
+	cmd |= ARL_STRTDN;
+	if (op)
+		cmd |= ARL_RW;
+	else
+		cmd &= ~ARL_RW;
+	core_writel(priv, cmd, CORE_ARLA_RWCTL);
+
+	return bcm_sf2_arl_op_wait(priv);
+}
+
+static int bcm_sf2_arl_read(struct bcm_sf2_priv *priv, u64 mac,
+			    u16 vid, struct bcm_sf2_arl_entry *ent, u8 *idx,
+			    bool is_valid)
+{
+	unsigned int i;
+	int ret;
+
+	ret = bcm_sf2_arl_op_wait(priv);
+	if (ret)
+		return ret;
+
+	/* Read the 4 bins */
+	for (i = 0; i < 4; i++) {
+		u64 mac_vid;
+		u32 fwd_entry;
+
+		mac_vid = core_readq(priv, CORE_ARLA_MACVID_ENTRY(i));
+		fwd_entry = core_readl(priv, CORE_ARLA_FWD_ENTRY(i));
+		bcm_sf2_arl_to_entry(ent, mac_vid, fwd_entry);
+
+		if (ent->is_valid && is_valid) {
+			*idx = i;
+			return 0;
+		}
+
+		/* This is the MAC we just deleted */
+		if (!is_valid && (mac_vid & mac))
+			return 0;
+	}
+
+	return -ENOENT;
+}
+
+static int bcm_sf2_arl_op(struct bcm_sf2_priv *priv, int op, int port,
+			  const unsigned char *addr, u16 vid, bool is_valid)
+{
+	struct bcm_sf2_arl_entry ent;
+	u32 fwd_entry;
+	u64 mac, mac_vid = 0;
+	u8 idx = 0;
+	int ret;
+
+	/* Convert the array into a 64-bit MAC */
+	mac = bcm_sf2_mac_to_u64(addr);
+
+	/* Perform a read for the given MAC and VID */
+	core_writeq(priv, mac, CORE_ARLA_MAC);
+	core_writel(priv, vid, CORE_ARLA_VID);
+
+	/* Issue a read operation for this MAC */
+	ret = bcm_sf2_arl_rw_op(priv, 1);
+	if (ret)
+		return ret;
+
+	ret = bcm_sf2_arl_read(priv, mac, vid, &ent, &idx, is_valid);
+	/* If this is a read, just finish now */
+	if (op)
+		return ret;
+
+	/* We could not find a matching MAC, so reset to a new entry */
+	if (ret) {
+		fwd_entry = 0;
+		idx = 0;
+	}
+
+	memset(&ent, 0, sizeof(ent));
+	ent.port = port;
+	ent.is_valid = is_valid;
+	ent.vid = vid;
+	ent.is_static = true;
+	memcpy(ent.mac, addr, ETH_ALEN);
+	bcm_sf2_arl_from_entry(&mac_vid, &fwd_entry, &ent);
+
+	core_writeq(priv, mac_vid, CORE_ARLA_MACVID_ENTRY(idx));
+	core_writel(priv, fwd_entry, CORE_ARLA_FWD_ENTRY(idx));
+
+	ret = bcm_sf2_arl_rw_op(priv, 0);
+	if (ret)
+		return ret;
+
+	/* Re-read the entry to check */
+	return bcm_sf2_arl_read(priv, mac, vid, &ent, &idx, is_valid);
+}
+
+static int bcm_sf2_sw_fdb_prepare(struct dsa_switch *ds, int port,
+				  const struct switchdev_obj_port_fdb *fdb,
+				  struct switchdev_trans *trans)
+{
+	/* We do not need to do anything specific here yet */
+	return 0;
+}
+
+static int bcm_sf2_sw_fdb_add(struct dsa_switch *ds, int port,
+			      const struct switchdev_obj_port_fdb *fdb,
+			      struct switchdev_trans *trans)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+
+	return bcm_sf2_arl_op(priv, 0, port, fdb->addr, fdb->vid, true);
+}
+
+static int bcm_sf2_sw_fdb_del(struct dsa_switch *ds, int port,
+			      const struct switchdev_obj_port_fdb *fdb)
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+
+	return bcm_sf2_arl_op(priv, 0, port, fdb->addr, fdb->vid, false);
+}
+
+static int bcm_sf2_arl_search_wait(struct bcm_sf2_priv *priv)
+{
+	unsigned timeout = 1000;
+	u32 reg;
+
+	do {
+		reg = core_readl(priv, CORE_ARLA_SRCH_CTL);
+		if (!(reg & ARLA_SRCH_STDN))
+			return 0;
+
+		if (reg & ARLA_SRCH_VLID)
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout--);
+
+	return -ETIMEDOUT;
+}
+
+static void bcm_sf2_arl_search_rd(struct bcm_sf2_priv *priv, u8 idx,
+				  struct bcm_sf2_arl_entry *ent)
+{
+	u64 mac_vid;
+	u32 fwd_entry;
+
+	mac_vid = core_readq(priv, CORE_ARLA_SRCH_RSLT_MACVID(idx));
+	fwd_entry = core_readl(priv, CORE_ARLA_SRCH_RSLT(idx));
+	bcm_sf2_arl_to_entry(ent, mac_vid, fwd_entry);
+}
+
+static int bcm_sf2_sw_fdb_copy(struct net_device *dev, int port,
+			       const struct bcm_sf2_arl_entry *ent,
+			       struct switchdev_obj_port_fdb *fdb,
+			       int (*cb)(struct switchdev_obj *obj))
+{
+	if (!ent->is_valid)
+		return 0;
+
+	if (port != ent->port)
+		return 0;
+
+	ether_addr_copy(fdb->addr, ent->mac);
+	fdb->vid = ent->vid;
+	fdb->ndm_state = ent->is_static ? NUD_NOARP : NUD_REACHABLE;
+
+	return cb(&fdb->obj);
+}
+
+static int bcm_sf2_sw_fdb_dump(struct dsa_switch *ds, int port,
+			       struct switchdev_obj_port_fdb *fdb,
+			       int (*cb)(struct switchdev_obj *obj))
+{
+	struct bcm_sf2_priv *priv = ds_to_priv(ds);
+	struct net_device *dev = ds->ports[port];
+	struct bcm_sf2_arl_entry results[2];
+	unsigned int count = 0;
+	int ret;
+
+	/* Start search operation */
+	core_writel(priv, ARLA_SRCH_STDN, CORE_ARLA_SRCH_CTL);
+
+	do {
+		ret = bcm_sf2_arl_search_wait(priv);
+		if (ret)
+			return ret;
+
+		/* Read both entries, then return their values back */
+		bcm_sf2_arl_search_rd(priv, 0, &results[0]);
+		ret = bcm_sf2_sw_fdb_copy(dev, port, &results[0], fdb, cb);
+		if (ret)
+			return ret;
+
+		bcm_sf2_arl_search_rd(priv, 1, &results[1]);
+		ret = bcm_sf2_sw_fdb_copy(dev, port, &results[1], fdb, cb);
+		if (ret)
+			return ret;
+
+		if (!results[0].is_valid && !results[1].is_valid)
+			break;
+
+	} while (count++ < CORE_ARLA_NUM_ENTRIES);
+
+	return 0;
+}
+
 static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id)
 {
 	struct bcm_sf2_priv *priv = dev_id;
@@ -615,6 +890,42 @@ static void bcm_sf2_intr_disable(struct bcm_sf2_priv *priv)
 	intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
 }
 
+static void bcm_sf2_identify_ports(struct bcm_sf2_priv *priv,
+				   struct device_node *dn)
+{
+	struct device_node *port;
+	const char *phy_mode_str;
+	int mode;
+	unsigned int port_num;
+	int ret;
+
+	priv->moca_port = -1;
+
+	for_each_available_child_of_node(dn, port) {
+		if (of_property_read_u32(port, "reg", &port_num))
+			continue;
+
+		/* Internal PHYs get assigned a specific 'phy-mode' property
+		 * value: "internal" to help flag them before MDIO probing
+		 * has completed, since they might be turned off at that
+		 * time
+		 */
+		mode = of_get_phy_mode(port);
+		if (mode < 0) {
+			ret = of_property_read_string(port, "phy-mode",
+						      &phy_mode_str);
+			if (ret < 0)
+				continue;
+
+			if (!strcasecmp(phy_mode_str, "internal"))
+				priv->int_phy_mask |= 1 << port_num;
+		}
+
+		if (mode == PHY_INTERFACE_MODE_MOCA)
+			priv->moca_port = port_num;
+	}
+}
+
 static int bcm_sf2_sw_setup(struct dsa_switch *ds)
 {
 	const char *reg_names[BCM_SF2_REGS_NUM] = BCM_SF2_REGS_NAME;
@@ -633,6 +944,7 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds)
 	 * level
 	 */
 	dn = ds->pd->of_node->parent;
+	bcm_sf2_identify_ports(priv, ds->pd->of_node);
 
 	priv->irq0 = irq_of_parse_and_map(dn, 0);
 	priv->irq1 = irq_of_parse_and_map(dn, 1);
@@ -913,7 +1225,7 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 
 	status->link = 0;
 
-	/* Port 7 is special as we do not get link status from CORE_LNKSTS,
+	/* MoCA port is special as we do not get link status from CORE_LNKSTS,
 	 * which means that we need to force the link at the port override
 	 * level to get the data to flow. We do use what the interrupt handler
 	 * did determine before.
@@ -921,7 +1233,7 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 	 * For the other ports, we just force the link status, since this is
 	 * a fixed PHY device.
 	 */
-	if (port == 7) {
+	if (port == priv->moca_port) {
 		status->link = priv->port_sts[port].link;
 		/* For MoCA interfaces, also force a link down notification
 		 * since some version of the user-space daemon (mocad) use
@@ -1076,6 +1388,10 @@ static struct dsa_switch_driver bcm_sf2_switch_driver = {
 	.port_join_bridge	= bcm_sf2_sw_br_join,
 	.port_leave_bridge	= bcm_sf2_sw_br_leave,
 	.port_stp_update	= bcm_sf2_sw_br_set_stp_state,
+	.port_fdb_prepare	= bcm_sf2_sw_fdb_prepare,
+	.port_fdb_add		= bcm_sf2_sw_fdb_add,
+	.port_fdb_del		= bcm_sf2_sw_fdb_del,
+	.port_fdb_dump		= bcm_sf2_sw_fdb_dump,
 };
 
 static int __init bcm_sf2_init(void)