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

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 131 insertions, 5 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ed458b3..7b8e39a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -92,6 +92,7 @@
 #ifdef CONFIG_INET
 #include <net/inet_common.h>
 #endif
+#include <linux/bpf.h>
 
 #include "internal.h"
 
@@ -518,13 +519,11 @@ static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc)
 }
 
 static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
-		int tx_ring,
 		struct sk_buff_head *rb_queue)
 {
 	struct tpacket_kbdq_core *pkc;
 
-	pkc = tx_ring ? GET_PBDQC_FROM_RB(&po->tx_ring) :
-			GET_PBDQC_FROM_RB(&po->rx_ring);
+	pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
 
 	spin_lock_bh(&rb_queue->lock);
 	pkc->delete_blk_timer = 1;
@@ -1412,6 +1411,22 @@ static unsigned int fanout_demux_qm(struct packet_fanout *f,
 	return skb_get_queue_mapping(skb) % num;
 }
 
+static unsigned int fanout_demux_bpf(struct packet_fanout *f,
+				     struct sk_buff *skb,
+				     unsigned int num)
+{
+	struct bpf_prog *prog;
+	unsigned int ret = 0;
+
+	rcu_read_lock();
+	prog = rcu_dereference(f->bpf_prog);
+	if (prog)
+		ret = BPF_PROG_RUN(prog, skb) % num;
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static bool fanout_has_flag(struct packet_fanout *f, u16 flag)
 {
 	return f->flags & (flag >> 8);
@@ -1456,6 +1471,10 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 	case PACKET_FANOUT_ROLLOVER:
 		idx = fanout_demux_rollover(f, skb, 0, false, num);
 		break;
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
+		idx = fanout_demux_bpf(f, skb, num);
+		break;
 	}
 
 	if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER))
@@ -1504,6 +1523,103 @@ static bool match_fanout_group(struct packet_type *ptype, struct sock *sk)
 	return false;
 }
 
+static void fanout_init_data(struct packet_fanout *f)
+{
+	switch (f->type) {
+	case PACKET_FANOUT_LB:
+		atomic_set(&f->rr_cur, 0);
+		break;
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
+		RCU_INIT_POINTER(f->bpf_prog, NULL);
+		break;
+	}
+}
+
+static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new)
+{
+	struct bpf_prog *old;
+
+	spin_lock(&f->lock);
+	old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock));
+	rcu_assign_pointer(f->bpf_prog, new);
+	spin_unlock(&f->lock);
+
+	if (old) {
+		synchronize_net();
+		bpf_prog_destroy(old);
+	}
+}
+
+static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data,
+				unsigned int len)
+{
+	struct bpf_prog *new;
+	struct sock_fprog fprog;
+	int ret;
+
+	if (sock_flag(&po->sk, SOCK_FILTER_LOCKED))
+		return -EPERM;
+	if (len != sizeof(fprog))
+		return -EINVAL;
+	if (copy_from_user(&fprog, data, len))
+		return -EFAULT;
+
+	ret = bpf_prog_create_from_user(&new, &fprog, NULL);
+	if (ret)
+		return ret;
+
+	__fanout_set_data_bpf(po->fanout, new);
+	return 0;
+}
+
+static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data,
+				unsigned int len)
+{
+	struct bpf_prog *new;
+	u32 fd;
+
+	if (sock_flag(&po->sk, SOCK_FILTER_LOCKED))
+		return -EPERM;
+	if (len != sizeof(fd))
+		return -EINVAL;
+	if (copy_from_user(&fd, data, len))
+		return -EFAULT;
+
+	new = bpf_prog_get(fd);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
+	if (new->type != BPF_PROG_TYPE_SOCKET_FILTER) {
+		bpf_prog_put(new);
+		return -EINVAL;
+	}
+
+	__fanout_set_data_bpf(po->fanout, new);
+	return 0;
+}
+
+static int fanout_set_data(struct packet_sock *po, char __user *data,
+			   unsigned int len)
+{
+	switch (po->fanout->type) {
+	case PACKET_FANOUT_CBPF:
+		return fanout_set_data_cbpf(po, data, len);
+	case PACKET_FANOUT_EBPF:
+		return fanout_set_data_ebpf(po, data, len);
+	default:
+		return -EINVAL;
+	};
+}
+
+static void fanout_release_data(struct packet_fanout *f)
+{
+	switch (f->type) {
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
+		__fanout_set_data_bpf(f, NULL);
+	};
+}
+
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
 	struct packet_sock *po = pkt_sk(sk);
@@ -1521,6 +1637,8 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	case PACKET_FANOUT_CPU:
 	case PACKET_FANOUT_RND:
 	case PACKET_FANOUT_QM:
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
 		break;
 	default:
 		return -EINVAL;
@@ -1563,10 +1681,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->id = id;
 		match->type = type;
 		match->flags = flags;
-		atomic_set(&match->rr_cur, 0);
 		INIT_LIST_HEAD(&match->list);
 		spin_lock_init(&match->lock);
 		atomic_set(&match->sk_ref, 0);
+		fanout_init_data(match);
 		match->prot_hook.type = po->prot_hook.type;
 		match->prot_hook.dev = po->prot_hook.dev;
 		match->prot_hook.func = packet_rcv_fanout;
@@ -1612,6 +1730,7 @@ static void fanout_release(struct sock *sk)
 	if (atomic_dec_and_test(&f->sk_ref)) {
 		list_del(&f->list);
 		dev_remove_pack(&f->prot_hook);
+		fanout_release_data(f);
 		kfree(f);
 	}
 	mutex_unlock(&fanout_mutex);
@@ -3531,6 +3650,13 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		return fanout_add(sk, val & 0xffff, val >> 16);
 	}
+	case PACKET_FANOUT_DATA:
+	{
+		if (!po->fanout)
+			return -EINVAL;
+
+		return fanout_set_data(po, optval, optlen);
+	}
 	case PACKET_TX_HAS_OFF:
 	{
 		unsigned int val;
@@ -4043,7 +4169,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	if (closing && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */
 		if (!tx_ring)
-			prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue);
+			prb_shutdown_retire_blk_timer(po, rb_queue);
 	}
 	release_sock(sk);