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

Pull networking updates from David Miller:

 1) More iov_iter conversion work from Al Viro.

    [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
      wrong, and this pull actually adds an extra commit on top of the
      branch I'm pulling to fix that up, so that the pre-merge state is
      ok.   - Linus ]

 2) Various optimizations to the ipv4 forwarding information base trie
    lookup implementation.  From Alexander Duyck.

 3) Remove sock_iocb altogether, from CHristoph Hellwig.

 4) Allow congestion control algorithm selection via routing metrics.
    From Daniel Borkmann.

 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.

 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.

 7) Add xmit_more support to r8169, e1000, and e1000e drivers.  From
    Florian Westphal.

 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.

 9) Add BPF packet actions to packet scheduler, from Jiri Pirko.

10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.

11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
    Kwok.

12) More sanely handle out-of-window dupacks, which can result in
    serious ACK storms.  From Neal Cardwell.

13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
    Patrick McHardy, and Thomas Graf.

14) Support xmit_more in be2net, from Sathya Perla.

15) Group Policy extensions for vxlan, from Thomas Graf.

16) Remove Checksum Offload support for vxlan, from Tom Herbert.

17) Like ipv4, support lockless transmit over ipv6 UDP sockets.  From
    Vlad Yasevich.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
  crypto: fix af_alg_make_sg() conversion to iov_iter
  ipv4: Namespecify TCP PMTU mechanism
  i40e: Fix for stats init function call in Rx setup
  tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
  openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
  ipv6: Make __ipv6_select_ident static
  ipv6: Fix fragment id assignment on LE arches.
  bridge: Fix inability to add non-vlan fdb entry
  net: Mellanox: Delete unnecessary checks before the function call "vunmap"
  cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
  ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
  net: dsa: Remove redundant phy_attach()
  IB/mlx4: Reset flow support for IB kernel ULPs
  IB/mlx4: Always use the correct port for mirrored multicast attachments
  net/bonding: Fix potential bad memory access during bonding events
  tipc: remove tipc_snprintf
  tipc: nl compat add noop and remove legacy nl framework
  tipc: convert legacy nl stats show to nl compat
  tipc: convert legacy nl net id get to nl compat
  tipc: convert legacy nl net id set to nl compat
  ...

1 files changed, 136 insertions, 75 deletions

diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 394a200..5a4828b 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -17,7 +17,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/skbuff.h>
-#include <linux/rculist.h>
+#include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/in.h>
 #include <linux/ip.h>
@@ -26,8 +26,8 @@
 #include <linux/etherdevice.h>
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
-#include <linux/hash.h>
 #include <linux/ethtool.h>
+#include <linux/mutex.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
 #include <net/ip.h>
@@ -50,38 +50,30 @@
 #include <net/ip6_checksum.h>
 #endif
 
-#define PORT_HASH_BITS 8
-#define PORT_HASH_SIZE (1<<PORT_HASH_BITS)
+/* Protects sock_list and refcounts. */
+static DEFINE_MUTEX(geneve_mutex);
 
 /* per-network namespace private data for this module */
 struct geneve_net {
-	struct hlist_head	sock_list[PORT_HASH_SIZE];
-	spinlock_t		sock_lock;   /* Protects sock_list */
+	struct list_head	sock_list;
 };
 
 static int geneve_net_id;
 
-static struct workqueue_struct *geneve_wq;
-
 static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
 {
 	return (struct genevehdr *)(udp_hdr(skb) + 1);
 }
 
-static struct hlist_head *gs_head(struct net *net, __be16 port)
+static struct geneve_sock *geneve_find_sock(struct net *net,
+					    sa_family_t family, __be16 port)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
-
-	return &gn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
-}
-
-/* Find geneve socket based on network namespace and UDP port */
-static struct geneve_sock *geneve_find_sock(struct net *net, __be16 port)
-{
 	struct geneve_sock *gs;
 
-	hlist_for_each_entry_rcu(gs, gs_head(net, port), hlist) {
-		if (inet_sk(gs->sock->sk)->inet_sport == port)
+	list_for_each_entry(gs, &gn->sock_list, list) {
+		if (inet_sk(gs->sock->sk)->inet_sport == port &&
+		    inet_sk(gs->sock->sk)->sk.sk_family == family)
 			return gs;
 	}
 
@@ -115,19 +107,19 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 		    struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
 		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
 		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
-		    bool xnet)
+		    bool csum, bool xnet)
 {
 	struct genevehdr *gnvh;
 	int min_headroom;
 	int err;
 
-	skb = udp_tunnel_handle_offloads(skb, !gs->sock->sk->sk_no_check_tx);
+	skb = udp_tunnel_handle_offloads(skb, csum);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr)
-			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	err = skb_cow_head(skb, min_headroom);
 	if (unlikely(err)) {
@@ -144,11 +136,107 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
-	return udp_tunnel_xmit_skb(gs->sock, rt, skb, src, dst,
-				   tos, ttl, df, src_port, dst_port, xnet);
+	return udp_tunnel_xmit_skb(rt, skb, src, dst,
+				   tos, ttl, df, src_port, dst_port, xnet,
+				   !csum);
 }
 EXPORT_SYMBOL_GPL(geneve_xmit_skb);
 
+static int geneve_hlen(struct genevehdr *gh)
+{
+	return sizeof(*gh) + gh->opt_len * 4;
+}
+
+static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
+					   struct sk_buff *skb,
+					   struct udp_offload *uoff)
+{
+	struct sk_buff *p, **pp = NULL;
+	struct genevehdr *gh, *gh2;
+	unsigned int hlen, gh_len, off_gnv;
+	const struct packet_offload *ptype;
+	__be16 type;
+	int flush = 1;
+
+	off_gnv = skb_gro_offset(skb);
+	hlen = off_gnv + sizeof(*gh);
+	gh = skb_gro_header_fast(skb, off_gnv);
+	if (skb_gro_header_hard(skb, hlen)) {
+		gh = skb_gro_header_slow(skb, hlen, off_gnv);
+		if (unlikely(!gh))
+			goto out;
+	}
+
+	if (gh->ver != GENEVE_VER || gh->oam)
+		goto out;
+	gh_len = geneve_hlen(gh);
+
+	hlen = off_gnv + gh_len;
+	if (skb_gro_header_hard(skb, hlen)) {
+		gh = skb_gro_header_slow(skb, hlen, off_gnv);
+		if (unlikely(!gh))
+			goto out;
+	}
+
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		gh2 = (struct genevehdr *)(p->data + off_gnv);
+		if (gh->opt_len != gh2->opt_len ||
+		    memcmp(gh, gh2, gh_len)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+	}
+
+	type = gh->proto_type;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (ptype == NULL) {
+		flush = 1;
+		goto out_unlock;
+	}
+
+	skb_gro_pull(skb, gh_len);
+	skb_gro_postpull_rcsum(skb, gh, gh_len);
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+static int geneve_gro_complete(struct sk_buff *skb, int nhoff,
+			       struct udp_offload *uoff)
+{
+	struct genevehdr *gh;
+	struct packet_offload *ptype;
+	__be16 type;
+	int gh_len;
+	int err = -ENOSYS;
+
+	udp_tunnel_gro_complete(skb, nhoff);
+
+	gh = (struct genevehdr *)(skb->data + nhoff);
+	gh_len = geneve_hlen(gh);
+	type = gh->proto_type;
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype != NULL)
+		err = ptype->callbacks.gro_complete(skb, nhoff + gh_len);
+
+	rcu_read_unlock();
+	return err;
+}
+
 static void geneve_notify_add_rx_port(struct geneve_sock *gs)
 {
 	struct sock *sk = gs->sock->sk;
@@ -214,15 +302,6 @@ error:
 	return 1;
 }
 
-static void geneve_del_work(struct work_struct *work)
-{
-	struct geneve_sock *gs = container_of(work, struct geneve_sock,
-					      del_work);
-
-	udp_tunnel_sock_release(gs->sock);
-	kfree_rcu(gs, rcu);
-}
-
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
 					 __be16 port)
 {
@@ -263,8 +342,6 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	if (!gs)
 		return ERR_PTR(-ENOMEM);
 
-	INIT_WORK(&gs->del_work, geneve_del_work);
-
 	sock = geneve_create_sock(net, ipv6, port);
 	if (IS_ERR(sock)) {
 		kfree(gs);
@@ -272,19 +349,15 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	}
 
 	gs->sock = sock;
-	atomic_set(&gs->refcnt, 1);
+	gs->refcnt = 1;
 	gs->rcv = rcv;
 	gs->rcv_data = data;
 
 	/* Initialize the geneve udp offloads structure */
 	gs->udp_offloads.port = port;
-	gs->udp_offloads.callbacks.gro_receive = NULL;
-	gs->udp_offloads.callbacks.gro_complete = NULL;
-
-	spin_lock(&gn->sock_lock);
-	hlist_add_head_rcu(&gs->hlist, gs_head(net, port));
+	gs->udp_offloads.callbacks.gro_receive  = geneve_gro_receive;
+	gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete;
 	geneve_notify_add_rx_port(gs);
-	spin_unlock(&gn->sock_lock);
 
 	/* Mark socket as an encapsulation socket */
 	tunnel_cfg.sk_user_data = gs;
@@ -293,6 +366,8 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	tunnel_cfg.encap_destroy = NULL;
 	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
 
+	list_add(&gs->list, &gn->sock_list);
+
 	return gs;
 }
 
@@ -300,25 +375,21 @@ struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
 				    geneve_rcv_t *rcv, void *data,
 				    bool no_share, bool ipv6)
 {
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
 
-	gs = geneve_socket_create(net, port, rcv, data, ipv6);
-	if (!IS_ERR(gs))
-		return gs;
-
-	if (no_share)	/* Return error if sharing is not allowed. */
-		return ERR_PTR(-EINVAL);
+	mutex_lock(&geneve_mutex);
 
-	spin_lock(&gn->sock_lock);
-	gs = geneve_find_sock(net, port);
-	if (gs && ((gs->rcv != rcv) ||
-		   !atomic_add_unless(&gs->refcnt, 1, 0)))
+	gs = geneve_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
+	if (gs) {
+		if (!no_share && gs->rcv == rcv)
+			gs->refcnt++;
+		else
 			gs = ERR_PTR(-EBUSY);
-	spin_unlock(&gn->sock_lock);
+	} else {
+		gs = geneve_socket_create(net, port, rcv, data, ipv6);
+	}
 
-	if (!gs)
-		gs = ERR_PTR(-EINVAL);
+	mutex_unlock(&geneve_mutex);
 
 	return gs;
 }
@@ -326,37 +397,32 @@ EXPORT_SYMBOL_GPL(geneve_sock_add);
 
 void geneve_sock_release(struct geneve_sock *gs)
 {
-	struct net *net = sock_net(gs->sock->sk);
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	mutex_lock(&geneve_mutex);
 
-	if (!atomic_dec_and_test(&gs->refcnt))
-		return;
+	if (--gs->refcnt)
+		goto unlock;
 
-	spin_lock(&gn->sock_lock);
-	hlist_del_rcu(&gs->hlist);
+	list_del(&gs->list);
 	geneve_notify_del_rx_port(gs);
-	spin_unlock(&gn->sock_lock);
+	udp_tunnel_sock_release(gs->sock);
+	kfree_rcu(gs, rcu);
 
-	queue_work(geneve_wq, &gs->del_work);
+unlock:
+	mutex_unlock(&geneve_mutex);
 }
 EXPORT_SYMBOL_GPL(geneve_sock_release);
 
 static __net_init int geneve_init_net(struct net *net)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
-	unsigned int h;
 
-	spin_lock_init(&gn->sock_lock);
-
-	for (h = 0; h < PORT_HASH_SIZE; ++h)
-		INIT_HLIST_HEAD(&gn->sock_list[h]);
+	INIT_LIST_HEAD(&gn->sock_list);
 
 	return 0;
 }
 
 static struct pernet_operations geneve_net_ops = {
 	.init = geneve_init_net,
-	.exit = NULL,
 	.id   = &geneve_net_id,
 	.size = sizeof(struct geneve_net),
 };
@@ -365,10 +431,6 @@ static int __init geneve_init_module(void)
 {
 	int rc;
 
-	geneve_wq = alloc_workqueue("geneve", 0, 0);
-	if (!geneve_wq)
-		return -ENOMEM;
-
 	rc = register_pernet_subsys(&geneve_net_ops);
 	if (rc)
 		return rc;
@@ -377,11 +439,10 @@ static int __init geneve_init_module(void)
 
 	return 0;
 }
-late_initcall(geneve_init_module);
+module_init(geneve_init_module);
 
 static void __exit geneve_cleanup_module(void)
 {
-	destroy_workqueue(geneve_wq);
 	unregister_pernet_subsys(&geneve_net_ops);
 }
 module_exit(geneve_cleanup_module);