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

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

1 files changed, 315 insertions, 0 deletions

diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
new file mode 100644
index 000000000000..538e9831c699
--- /dev/null
+++ b/net/rxrpc/peer_object.c
@@ -0,0 +1,315 @@
+/* RxRPC remote transport endpoint record management
+ *
+ * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <linux/in.h>
+#include <linux/slab.h>
+#include <linux/hashtable.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include "ar-internal.h"
+
+static DEFINE_HASHTABLE(rxrpc_peer_hash, 10);
+static DEFINE_SPINLOCK(rxrpc_peer_hash_lock);
+
+/*
+ * Hash a peer key.
+ */
+static unsigned long rxrpc_peer_hash_key(struct rxrpc_local *local,
+					 const struct sockaddr_rxrpc *srx)
+{
+	const u16 *p;
+	unsigned int i, size;
+	unsigned long hash_key;
+
+	_enter("");
+
+	hash_key = (unsigned long)local / __alignof__(*local);
+	hash_key += srx->transport_type;
+	hash_key += srx->transport_len;
+	hash_key += srx->transport.family;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		hash_key += (u16 __force)srx->transport.sin.sin_port;
+		size = sizeof(srx->transport.sin.sin_addr);
+		p = (u16 *)&srx->transport.sin.sin_addr;
+		break;
+	default:
+		WARN(1, "AF_RXRPC: Unsupported transport address family\n");
+		return 0;
+	}
+
+	/* Step through the peer address in 16-bit portions for speed */
+	for (i = 0; i < size; i += sizeof(*p), p++)
+		hash_key += *p;
+
+	_leave(" 0x%lx", hash_key);
+	return hash_key;
+}
+
+/*
+ * Compare a peer to a key.  Return -ve, 0 or +ve to indicate less than, same
+ * or greater than.
+ *
+ * Unfortunately, the primitives in linux/hashtable.h don't allow for sorted
+ * buckets and mid-bucket insertion, so we don't make full use of this
+ * information at this point.
+ */
+static long rxrpc_peer_cmp_key(const struct rxrpc_peer *peer,
+			       struct rxrpc_local *local,
+			       const struct sockaddr_rxrpc *srx,
+			       unsigned long hash_key)
+{
+	long diff;
+
+	diff = ((peer->hash_key - hash_key) ?:
+		((unsigned long)peer->local - (unsigned long)local) ?:
+		(peer->srx.transport_type - srx->transport_type) ?:
+		(peer->srx.transport_len - srx->transport_len) ?:
+		(peer->srx.transport.family - srx->transport.family));
+	if (diff != 0)
+		return diff;
+
+	switch (srx->transport.family) {
+	case AF_INET:
+		return ((u16 __force)peer->srx.transport.sin.sin_port -
+			(u16 __force)srx->transport.sin.sin_port) ?:
+			memcmp(&peer->srx.transport.sin.sin_addr,
+			       &srx->transport.sin.sin_addr,
+			       sizeof(struct in_addr));
+	default:
+		BUG();
+	}
+}
+
+/*
+ * Look up a remote transport endpoint for the specified address using RCU.
+ */
+static struct rxrpc_peer *__rxrpc_lookup_peer_rcu(
+	struct rxrpc_local *local,
+	const struct sockaddr_rxrpc *srx,
+	unsigned long hash_key)
+{
+	struct rxrpc_peer *peer;
+
+	hash_for_each_possible_rcu(rxrpc_peer_hash, peer, hash_link, hash_key) {
+		if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) {
+			if (atomic_read(&peer->usage) == 0)
+				return NULL;
+			return peer;
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * Look up a remote transport endpoint for the specified address using RCU.
+ */
+struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local,
+					 const struct sockaddr_rxrpc *srx)
+{
+	struct rxrpc_peer *peer;
+	unsigned long hash_key = rxrpc_peer_hash_key(local, srx);
+
+	peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+	if (peer) {
+		switch (srx->transport.family) {
+		case AF_INET:
+			_net("PEER %d {%d,%u,%pI4+%hu}",
+			     peer->debug_id,
+			     peer->srx.transport_type,
+			     peer->srx.transport.family,
+			     &peer->srx.transport.sin.sin_addr,
+			     ntohs(peer->srx.transport.sin.sin_port));
+			break;
+		}
+
+		_leave(" = %p {u=%d}", peer, atomic_read(&peer->usage));
+	}
+	return peer;
+}
+
+/*
+ * assess the MTU size for the network interface through which this peer is
+ * reached
+ */
+static void rxrpc_assess_MTU_size(struct rxrpc_peer *peer)
+{
+	struct rtable *rt;
+	struct flowi4 fl4;
+
+	peer->if_mtu = 1500;
+
+	rt = ip_route_output_ports(&init_net, &fl4, NULL,
+				   peer->srx.transport.sin.sin_addr.s_addr, 0,
+				   htons(7000), htons(7001),
+				   IPPROTO_UDP, 0, 0);
+	if (IS_ERR(rt)) {
+		_leave(" [route err %ld]", PTR_ERR(rt));
+		return;
+	}
+
+	peer->if_mtu = dst_mtu(&rt->dst);
+	dst_release(&rt->dst);
+
+	_leave(" [if_mtu %u]", peer->if_mtu);
+}
+
+/*
+ * Allocate a peer.
+ */
+struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
+{
+	struct rxrpc_peer *peer;
+
+	_enter("");
+
+	peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
+	if (peer) {
+		atomic_set(&peer->usage, 1);
+		peer->local = local;
+		INIT_HLIST_HEAD(&peer->error_targets);
+		INIT_WORK(&peer->error_distributor,
+			  &rxrpc_peer_error_distributor);
+		peer->service_conns = RB_ROOT;
+		seqlock_init(&peer->service_conn_lock);
+		spin_lock_init(&peer->lock);
+		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
+	}
+
+	_leave(" = %p", peer);
+	return peer;
+}
+
+/*
+ * Set up a new peer.
+ */
+static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
+					    struct sockaddr_rxrpc *srx,
+					    unsigned long hash_key,
+					    gfp_t gfp)
+{
+	struct rxrpc_peer *peer;
+
+	_enter("");
+
+	peer = rxrpc_alloc_peer(local, gfp);
+	if (peer) {
+		peer->hash_key = hash_key;
+		memcpy(&peer->srx, srx, sizeof(*srx));
+
+		rxrpc_assess_MTU_size(peer);
+		peer->mtu = peer->if_mtu;
+
+		if (srx->transport.family == AF_INET) {
+			peer->hdrsize = sizeof(struct iphdr);
+			switch (srx->transport_type) {
+			case SOCK_DGRAM:
+				peer->hdrsize += sizeof(struct udphdr);
+				break;
+			default:
+				BUG();
+				break;
+			}
+		} else {
+			BUG();
+		}
+
+		peer->hdrsize += sizeof(struct rxrpc_wire_header);
+		peer->maxdata = peer->mtu - peer->hdrsize;
+	}
+
+	_leave(" = %p", peer);
+	return peer;
+}
+
+/*
+ * obtain a remote transport endpoint for the specified address
+ */
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
+				     struct sockaddr_rxrpc *srx, gfp_t gfp)
+{
+	struct rxrpc_peer *peer, *candidate;
+	unsigned long hash_key = rxrpc_peer_hash_key(local, srx);
+
+	_enter("{%d,%d,%pI4+%hu}",
+	       srx->transport_type,
+	       srx->transport_len,
+	       &srx->transport.sin.sin_addr,
+	       ntohs(srx->transport.sin.sin_port));
+
+	/* search the peer list first */
+	rcu_read_lock();
+	peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+	if (peer && !rxrpc_get_peer_maybe(peer))
+		peer = NULL;
+	rcu_read_unlock();
+
+	if (!peer) {
+		/* The peer is not yet present in hash - create a candidate
+		 * for a new record and then redo the search.
+		 */
+		candidate = rxrpc_create_peer(local, srx, hash_key, gfp);
+		if (!candidate) {
+			_leave(" = NULL [nomem]");
+			return NULL;
+		}
+
+		spin_lock(&rxrpc_peer_hash_lock);
+
+		/* Need to check that we aren't racing with someone else */
+		peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
+		if (peer && !rxrpc_get_peer_maybe(peer))
+			peer = NULL;
+		if (!peer)
+			hash_add_rcu(rxrpc_peer_hash,
+				     &candidate->hash_link, hash_key);
+
+		spin_unlock(&rxrpc_peer_hash_lock);
+
+		if (peer)
+			kfree(candidate);
+		else
+			peer = candidate;
+	}
+
+	_net("PEER %d {%d,%pI4+%hu}",
+	     peer->debug_id,
+	     peer->srx.transport_type,
+	     &peer->srx.transport.sin.sin_addr,
+	     ntohs(peer->srx.transport.sin.sin_port));
+
+	_leave(" = %p {u=%d}", peer, atomic_read(&peer->usage));
+	return peer;
+}
+
+/*
+ * Discard a ref on a remote peer record.
+ */
+void __rxrpc_put_peer(struct rxrpc_peer *peer)
+{
+	ASSERT(hlist_empty(&peer->error_targets));
+
+	spin_lock(&rxrpc_peer_hash_lock);
+	hash_del_rcu(&peer->hash_link);
+	spin_unlock(&rxrpc_peer_hash_lock);
+
+	kfree_rcu(peer, rcu);
+}