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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 303 insertions, 4 deletions

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 726edabff26b..38b4fae61f04 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -35,7 +35,8 @@
 #include <net/xfrm.h>
 #include <linux/netpoll.h>
 
-#define MACVLAN_HASH_SIZE	(1 << BITS_PER_BYTE)
+#define MACVLAN_HASH_BITS	8
+#define MACVLAN_HASH_SIZE	(1<<MACVLAN_HASH_BITS)
 #define MACVLAN_BC_QUEUE_LEN	1000
 
 struct macvlan_port {
@@ -47,6 +48,14 @@ struct macvlan_port {
 	struct work_struct	bc_work;
 	bool 			passthru;
 	int			count;
+	struct hlist_head	vlan_source_hash[MACVLAN_HASH_SIZE];
+};
+
+struct macvlan_source_entry {
+	struct hlist_node	hlist;
+	struct macvlan_dev	*vlan;
+	unsigned char		addr[6+2] __aligned(sizeof(u16));
+	struct rcu_head		rcu;
 };
 
 struct macvlan_skb_cb {
@@ -57,6 +66,20 @@ struct macvlan_skb_cb {
 
 static void macvlan_port_destroy(struct net_device *dev);
 
+/* Hash Ethernet address */
+static u32 macvlan_eth_hash(const unsigned char *addr)
+{
+	u64 value = get_unaligned((u64 *)addr);
+
+	/* only want 6 bytes */
+#ifdef __BIG_ENDIAN
+	value >>= 16;
+#else
+	value <<= 16;
+#endif
+	return hash_64(value, MACVLAN_HASH_BITS);
+}
+
 static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev)
 {
 	return rcu_dereference(dev->rx_handler_data);
@@ -73,20 +96,68 @@ static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port,
 					       const unsigned char *addr)
 {
 	struct macvlan_dev *vlan;
+	u32 idx = macvlan_eth_hash(addr);
 
-	hlist_for_each_entry_rcu(vlan, &port->vlan_hash[addr[5]], hlist) {
+	hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist) {
 		if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr))
 			return vlan;
 	}
 	return NULL;
 }
 
+static struct macvlan_source_entry *macvlan_hash_lookup_source(
+	const struct macvlan_dev *vlan,
+	const unsigned char *addr)
+{
+	struct macvlan_source_entry *entry;
+	u32 idx = macvlan_eth_hash(addr);
+	struct hlist_head *h = &vlan->port->vlan_source_hash[idx];
+
+	hlist_for_each_entry_rcu(entry, h, hlist) {
+		if (ether_addr_equal_64bits(entry->addr, addr) &&
+		    entry->vlan == vlan)
+			return entry;
+	}
+	return NULL;
+}
+
+static int macvlan_hash_add_source(struct macvlan_dev *vlan,
+				   const unsigned char *addr)
+{
+	struct macvlan_port *port = vlan->port;
+	struct macvlan_source_entry *entry;
+	struct hlist_head *h;
+
+	entry = macvlan_hash_lookup_source(vlan, addr);
+	if (entry)
+		return 0;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	ether_addr_copy(entry->addr, addr);
+	entry->vlan = vlan;
+	h = &port->vlan_source_hash[macvlan_eth_hash(addr)];
+	hlist_add_head_rcu(&entry->hlist, h);
+	vlan->macaddr_count++;
+
+	return 0;
+}
+
 static void macvlan_hash_add(struct macvlan_dev *vlan)
 {
 	struct macvlan_port *port = vlan->port;
 	const unsigned char *addr = vlan->dev->dev_addr;
+	u32 idx = macvlan_eth_hash(addr);
 
-	hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[addr[5]]);
+	hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]);
+}
+
+static void macvlan_hash_del_source(struct macvlan_source_entry *entry)
+{
+	hlist_del_rcu(&entry->hlist);
+	kfree_rcu(entry, rcu);
 }
 
 static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync)
@@ -267,6 +338,65 @@ err:
 	atomic_long_inc(&skb->dev->rx_dropped);
 }
 
+static void macvlan_flush_sources(struct macvlan_port *port,
+				  struct macvlan_dev *vlan)
+{
+	int i;
+
+	for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
+		struct hlist_node *h, *n;
+
+		hlist_for_each_safe(h, n, &port->vlan_source_hash[i]) {
+			struct macvlan_source_entry *entry;
+
+			entry = hlist_entry(h, struct macvlan_source_entry,
+					    hlist);
+			if (entry->vlan == vlan)
+				macvlan_hash_del_source(entry);
+		}
+	}
+	vlan->macaddr_count = 0;
+}
+
+static void macvlan_forward_source_one(struct sk_buff *skb,
+				       struct macvlan_dev *vlan)
+{
+	struct sk_buff *nskb;
+	struct net_device *dev;
+	int len;
+	int ret;
+
+	dev = vlan->dev;
+	if (unlikely(!(dev->flags & IFF_UP)))
+		return;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return;
+
+	len = nskb->len + ETH_HLEN;
+	nskb->dev = dev;
+	nskb->pkt_type = PACKET_HOST;
+
+	ret = netif_rx(nskb);
+	macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, 0);
+}
+
+static void macvlan_forward_source(struct sk_buff *skb,
+				   struct macvlan_port *port,
+				   const unsigned char *addr)
+{
+	struct macvlan_source_entry *entry;
+	u32 idx = macvlan_eth_hash(addr);
+	struct hlist_head *h = &port->vlan_source_hash[idx];
+
+	hlist_for_each_entry_rcu(entry, h, hlist) {
+		if (ether_addr_equal_64bits(entry->addr, addr))
+			if (entry->vlan->dev->flags & IFF_UP)
+				macvlan_forward_source_one(skb, entry->vlan);
+	}
+}
+
 /* called under rcu_read_lock() from netif_receive_skb */
 static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 {
@@ -285,6 +415,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 		if (!skb)
 			return RX_HANDLER_CONSUMED;
 		eth = eth_hdr(skb);
+		macvlan_forward_source(skb, port, eth->h_source);
 		src = macvlan_hash_lookup(port, eth->h_source);
 		if (src && src->mode != MACVLAN_MODE_VEPA &&
 		    src->mode != MACVLAN_MODE_BRIDGE) {
@@ -301,6 +432,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 		return RX_HANDLER_PASS;
 	}
 
+	macvlan_forward_source(skb, port, eth->h_source);
 	if (port->passthru)
 		vlan = list_first_or_null_rcu(&port->vlans,
 					      struct macvlan_dev, list);
@@ -667,6 +799,7 @@ static void macvlan_uninit(struct net_device *dev)
 
 	free_percpu(vlan->pcpu_stats);
 
+	macvlan_flush_sources(port, vlan);
 	port->count -= 1;
 	if (!port->count)
 		macvlan_port_destroy(port->dev);
@@ -892,7 +1025,8 @@ void macvlan_common_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 
-	dev->priv_flags	       &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+	dev->priv_flags	       &= ~IFF_TX_SKB_SHARING;
+	netif_keep_dst(dev);
 	dev->priv_flags	       |= IFF_UNICAST_FLT;
 	dev->netdev_ops		= &macvlan_netdev_ops;
 	dev->destructor		= free_netdev;
@@ -925,6 +1059,8 @@ static int macvlan_port_create(struct net_device *dev)
 	INIT_LIST_HEAD(&port->vlans);
 	for (i = 0; i < MACVLAN_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&port->vlan_hash[i]);
+	for (i = 0; i < MACVLAN_HASH_SIZE; i++)
+		INIT_HLIST_HEAD(&port->vlan_source_hash[i]);
 
 	skb_queue_head_init(&port->bc_queue);
 	INIT_WORK(&port->bc_work, macvlan_process_broadcast);
@@ -966,11 +1102,102 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[])
 		case MACVLAN_MODE_VEPA:
 		case MACVLAN_MODE_BRIDGE:
 		case MACVLAN_MODE_PASSTHRU:
+		case MACVLAN_MODE_SOURCE:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+		switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) {
+		case MACVLAN_MACADDR_ADD:
+		case MACVLAN_MACADDR_DEL:
+		case MACVLAN_MACADDR_FLUSH:
+		case MACVLAN_MACADDR_SET:
 			break;
 		default:
 			return -EINVAL;
 		}
 	}
+
+	if (data && data[IFLA_MACVLAN_MACADDR]) {
+		if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN)
+			return -EINVAL;
+
+		if (!is_valid_ether_addr(nla_data(data[IFLA_MACVLAN_MACADDR])))
+			return -EADDRNOTAVAIL;
+	}
+
+	if (data && data[IFLA_MACVLAN_MACADDR_COUNT])
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * reconfigure list of remote source mac address
+ * (only for macvlan devices in source mode)
+ * Note regarding alignment: all netlink data is aligned to 4 Byte, which
+ * suffices for both ether_addr_copy and ether_addr_equal_64bits usage.
+ */
+static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
+				      struct nlattr *data[])
+{
+	char *addr = NULL;
+	int ret, rem, len;
+	struct nlattr *nla, *head;
+	struct macvlan_source_entry *entry;
+
+	if (data[IFLA_MACVLAN_MACADDR])
+		addr = nla_data(data[IFLA_MACVLAN_MACADDR]);
+
+	if (mode == MACVLAN_MACADDR_ADD) {
+		if (!addr)
+			return -EINVAL;
+
+		return macvlan_hash_add_source(vlan, addr);
+
+	} else if (mode == MACVLAN_MACADDR_DEL) {
+		if (!addr)
+			return -EINVAL;
+
+		entry = macvlan_hash_lookup_source(vlan, addr);
+		if (entry) {
+			macvlan_hash_del_source(entry);
+			vlan->macaddr_count--;
+		}
+	} else if (mode == MACVLAN_MACADDR_FLUSH) {
+		macvlan_flush_sources(vlan->port, vlan);
+	} else if (mode == MACVLAN_MACADDR_SET) {
+		macvlan_flush_sources(vlan->port, vlan);
+
+		if (addr) {
+			ret = macvlan_hash_add_source(vlan, addr);
+			if (ret)
+				return ret;
+		}
+
+		if (!data || !data[IFLA_MACVLAN_MACADDR_DATA])
+			return 0;
+
+		head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]);
+		len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]);
+
+		nla_for_each_attr(nla, head, len, rem) {
+			if (nla_type(nla) != IFLA_MACVLAN_MACADDR ||
+			    nla_len(nla) != ETH_ALEN)
+				continue;
+
+			addr = nla_data(nla);
+			ret = macvlan_hash_add_source(vlan, addr);
+			if (ret)
+				return ret;
+		}
+	} else {
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -981,6 +1208,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 	struct macvlan_port *port;
 	struct net_device *lowerdev;
 	int err;
+	int macmode;
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
@@ -1034,6 +1262,15 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 		eth_hw_addr_inherit(dev, lowerdev);
 	}
 
+	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+		if (vlan->mode != MACVLAN_MODE_SOURCE)
+			return -EINVAL;
+		macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]);
+		err = macvlan_changelink_sources(vlan, macmode, data);
+		if (err)
+			return err;
+	}
+
 	port->count += 1;
 	err = register_netdevice(dev);
 	if (err < 0)
@@ -1070,6 +1307,8 @@ void macvlan_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 
+	if (vlan->mode == MACVLAN_MODE_SOURCE)
+		macvlan_flush_sources(vlan->port, vlan);
 	list_del_rcu(&vlan->list);
 	unregister_netdevice_queue(dev, head);
 	netdev_upper_dev_unlink(vlan->lowerdev, dev);
@@ -1082,6 +1321,8 @@ static int macvlan_changelink(struct net_device *dev,
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	enum macvlan_mode mode;
 	bool set_mode = false;
+	enum macvlan_macaddr_mode macmode;
+	int ret;
 
 	/* Validate mode, but don't set yet: setting flags may fail. */
 	if (data && data[IFLA_MACVLAN_MODE]) {
@@ -1091,6 +1332,9 @@ static int macvlan_changelink(struct net_device *dev,
 		if ((mode == MACVLAN_MODE_PASSTHRU) !=
 		    (vlan->mode == MACVLAN_MODE_PASSTHRU))
 			return -EINVAL;
+		if (vlan->mode == MACVLAN_MODE_SOURCE &&
+		    vlan->mode != mode)
+			macvlan_flush_sources(vlan->port, vlan);
 	}
 
 	if (data && data[IFLA_MACVLAN_FLAGS]) {
@@ -1110,26 +1354,77 @@ static int macvlan_changelink(struct net_device *dev,
 	}
 	if (set_mode)
 		vlan->mode = mode;
+	if (data && data[IFLA_MACVLAN_MACADDR_MODE]) {
+		if (vlan->mode != MACVLAN_MODE_SOURCE)
+			return -EINVAL;
+		macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]);
+		ret = macvlan_changelink_sources(vlan, macmode, data);
+		if (ret)
+			return ret;
+	}
 	return 0;
 }
 
+static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan)
+{
+	if (vlan->macaddr_count == 0)
+		return 0;
+	return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */
+		+ vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN);
+}
+
 static size_t macvlan_get_size(const struct net_device *dev)
 {
+	struct macvlan_dev *vlan = netdev_priv(dev);
+
 	return (0
 		+ nla_total_size(4) /* IFLA_MACVLAN_MODE */
 		+ nla_total_size(2) /* IFLA_MACVLAN_FLAGS */
+		+ nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */
+		+ macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */
 		);
 }
 
+static int macvlan_fill_info_macaddr(struct sk_buff *skb,
+				     const struct macvlan_dev *vlan,
+				     const int i)
+{
+	struct hlist_head *h = &vlan->port->vlan_source_hash[i];
+	struct macvlan_source_entry *entry;
+
+	hlist_for_each_entry_rcu(entry, h, hlist) {
+		if (entry->vlan != vlan)
+			continue;
+		if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr))
+			return 1;
+	}
+	return 0;
+}
+
 static int macvlan_fill_info(struct sk_buff *skb,
 				const struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
+	int i;
+	struct nlattr *nest;
 
 	if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode))
 		goto nla_put_failure;
 	if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags))
 		goto nla_put_failure;
+	if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count))
+		goto nla_put_failure;
+	if (vlan->macaddr_count > 0) {
+		nest = nla_nest_start(skb, IFLA_MACVLAN_MACADDR_DATA);
+		if (nest == NULL)
+			goto nla_put_failure;
+
+		for (i = 0; i < MACVLAN_HASH_SIZE; i++) {
+			if (macvlan_fill_info_macaddr(skb, vlan, i))
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
+	}
 	return 0;
 
 nla_put_failure:
@@ -1139,6 +1434,10 @@ nla_put_failure:
 static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = {
 	[IFLA_MACVLAN_MODE]  = { .type = NLA_U32 },
 	[IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 },
+	[IFLA_MACVLAN_MACADDR_MODE] = { .type = NLA_U32 },
+	[IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+	[IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED },
+	[IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 },
 };
 
 int macvlan_link_register(struct rtnl_link_ops *ops)