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

Pull networking updates from David Miller:

 1) New offloading infrastructure and example 'rocker' driver for
    offloading of switching and routing to hardware.

    This work was done by a large group of dedicated individuals, not
    limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
    Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu

 2) Start making the networking operate on IOV iterators instead of
    modifying iov objects in-situ during transfers.  Thanks to Al Viro
    and Herbert Xu.

 3) A set of new netlink interfaces for the TIPC stack, from Richard
    Alpe.

 4) Remove unnecessary looping during ipv6 routing lookups, from Martin
    KaFai Lau.

 5) Add PAUSE frame generation support to gianfar driver, from Matei
    Pavaluca.

 6) Allow for larger reordering levels in TCP, which are easily
    achievable in the real world right now, from Eric Dumazet.

 7) Add a variable of napi_schedule that doesn't need to disable cpu
    interrupts, from Eric Dumazet.

 8) Use a doubly linked list to optimize neigh_parms_release(), from
    Nicolas Dichtel.

 9) Various enhancements to the kernel BPF verifier, and allow eBPF
    programs to actually be attached to sockets.  From Alexei
    Starovoitov.

10) Support TSO/LSO in sunvnet driver, from David L Stevens.

11) Allow controlling ECN usage via routing metrics, from Florian
    Westphal.

12) Remote checksum offload, from Tom Herbert.

13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
    driver, from Thomas Lendacky.

14) Add MPLS support to openvswitch, from Simon Horman.

15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
    Klassert.

16) Do gro flushes on a per-device basis using a timer, from Eric
    Dumazet.  This tries to resolve the conflicting goals between the
    desired handling of bulk vs.  RPC-like traffic.

17) Allow userspace to ask for the CPU upon what a packet was
    received/steered, via SO_INCOMING_CPU.  From Eric Dumazet.

18) Limit GSO packets to half the current congestion window, from Eric
    Dumazet.

19) Add a generic helper so that all drivers set their RSS keys in a
    consistent way, from Eric Dumazet.

20) Add xmit_more support to enic driver, from Govindarajulu
    Varadarajan.

21) Add VLAN packet scheduler action, from Jiri Pirko.

22) Support configurable RSS hash functions via ethtool, from Eyal
    Perry.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
  Fix race condition between vxlan_sock_add and vxlan_sock_release
  net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
  net/mlx4: Add support for A0 steering
  net/mlx4: Refactor QUERY_PORT
  net/mlx4_core: Add explicit error message when rule doesn't meet configuration
  net/mlx4: Add A0 hybrid steering
  net/mlx4: Add mlx4_bitmap zone allocator
  net/mlx4: Add a check if there are too many reserved QPs
  net/mlx4: Change QP allocation scheme
  net/mlx4_core: Use tasklet for user-space CQ completion events
  net/mlx4_core: Mask out host side virtualization features for guests
  net/mlx4_en: Set csum level for encapsulated packets
  be2net: Export tunnel offloads only when a VxLAN tunnel is created
  gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
  cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
  net: fec: only enable mdio interrupt before phy device link up
  net: fec: clear all interrupt events to support i.MX6SX
  net: fec: reset fep link status in suspend function
  net: sock: fix access via invalid file descriptor
  net: introduce helper macro for_each_cmsghdr
  ...

1 files changed, 125 insertions, 154 deletions

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ef31fef25e5a..8e38f17288d3 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -56,7 +56,6 @@ static void __neigh_notify(struct neighbour *n, int type, int flags);
 static void neigh_update_notify(struct neighbour *neigh);
 static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
 
-static struct neigh_table *neigh_tables;
 #ifdef CONFIG_PROC_FS
 static const struct file_operations neigh_stat_seq_fops;
 #endif
@@ -87,13 +86,8 @@ static const struct file_operations neigh_stat_seq_fops;
    the most complicated procedure, which we allow is dev->hard_header.
    It is supposed, that dev->hard_header is simplistic and does
    not make callbacks to neighbour tables.
-
-   The last lock is neigh_tbl_lock. It is pure SMP lock, protecting
-   list of neighbour tables. This list is used only in process context,
  */
 
-static DEFINE_RWLOCK(neigh_tbl_lock);
-
 static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb)
 {
 	kfree_skb(skb);
@@ -773,7 +767,7 @@ static void neigh_periodic_work(struct work_struct *work)
 	if (time_after(jiffies, tbl->last_rand + 300 * HZ)) {
 		struct neigh_parms *p;
 		tbl->last_rand = jiffies;
-		for (p = &tbl->parms; p; p = p->next)
+		list_for_each_entry(p, &tbl->parms_list, list)
 			p->reachable_time =
 				neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
 	}
@@ -1446,7 +1440,7 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
 {
 	struct neigh_parms *p;
 
-	for (p = &tbl->parms; p; p = p->next) {
+	list_for_each_entry(p, &tbl->parms_list, list) {
 		if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) ||
 		    (!p->dev && !ifindex && net_eq(net, &init_net)))
 			return p;
@@ -1481,8 +1475,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
 		}
 
 		write_lock_bh(&tbl->lock);
-		p->next		= tbl->parms.next;
-		tbl->parms.next = p;
+		list_add(&p->list, &tbl->parms.list);
 		write_unlock_bh(&tbl->lock);
 
 		neigh_parms_data_state_cleanall(p);
@@ -1501,24 +1494,15 @@ static void neigh_rcu_free_parms(struct rcu_head *head)
 
 void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
 {
-	struct neigh_parms **p;
-
 	if (!parms || parms == &tbl->parms)
 		return;
 	write_lock_bh(&tbl->lock);
-	for (p = &tbl->parms.next; *p; p = &(*p)->next) {
-		if (*p == parms) {
-			*p = parms->next;
-			parms->dead = 1;
-			write_unlock_bh(&tbl->lock);
-			if (parms->dev)
-				dev_put(parms->dev);
-			call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
-			return;
-		}
-	}
+	list_del(&parms->list);
+	parms->dead = 1;
 	write_unlock_bh(&tbl->lock);
-	neigh_dbg(1, "%s: not found\n", __func__);
+	if (parms->dev)
+		dev_put(parms->dev);
+	call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
 }
 EXPORT_SYMBOL(neigh_parms_release);
 
@@ -1530,11 +1514,15 @@ static void neigh_parms_destroy(struct neigh_parms *parms)
 
 static struct lock_class_key neigh_table_proxy_queue_class;
 
-static void neigh_table_init_no_netlink(struct neigh_table *tbl)
+static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly;
+
+void neigh_table_init(int index, struct neigh_table *tbl)
 {
 	unsigned long now = jiffies;
 	unsigned long phsize;
 
+	INIT_LIST_HEAD(&tbl->parms_list);
+	list_add(&tbl->parms.list, &tbl->parms_list);
 	write_pnet(&tbl->parms.net, &init_net);
 	atomic_set(&tbl->parms.refcnt, 1);
 	tbl->parms.reachable_time =
@@ -1574,34 +1562,14 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl)
 
 	tbl->last_flush = now;
 	tbl->last_rand	= now + tbl->parms.reachable_time * 20;
-}
-
-void neigh_table_init(struct neigh_table *tbl)
-{
-	struct neigh_table *tmp;
-
-	neigh_table_init_no_netlink(tbl);
-	write_lock(&neigh_tbl_lock);
-	for (tmp = neigh_tables; tmp; tmp = tmp->next) {
-		if (tmp->family == tbl->family)
-			break;
-	}
-	tbl->next	= neigh_tables;
-	neigh_tables	= tbl;
-	write_unlock(&neigh_tbl_lock);
 
-	if (unlikely(tmp)) {
-		pr_err("Registering multiple tables for family %d\n",
-		       tbl->family);
-		dump_stack();
-	}
+	neigh_tables[index] = tbl;
 }
 EXPORT_SYMBOL(neigh_table_init);
 
-int neigh_table_clear(struct neigh_table *tbl)
+int neigh_table_clear(int index, struct neigh_table *tbl)
 {
-	struct neigh_table **tp;
-
+	neigh_tables[index] = NULL;
 	/* It is not clean... Fix it to unload IPv6 module safely */
 	cancel_delayed_work_sync(&tbl->gc_work);
 	del_timer_sync(&tbl->proxy_timer);
@@ -1609,14 +1577,6 @@ int neigh_table_clear(struct neigh_table *tbl)
 	neigh_ifdown(tbl, NULL);
 	if (atomic_read(&tbl->entries))
 		pr_crit("neighbour leakage\n");
-	write_lock(&neigh_tbl_lock);
-	for (tp = &neigh_tables; *tp; tp = &(*tp)->next) {
-		if (*tp == tbl) {
-			*tp = tbl->next;
-			break;
-		}
-	}
-	write_unlock(&neigh_tbl_lock);
 
 	call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu,
 		 neigh_hash_free_rcu);
@@ -1634,12 +1594,32 @@ int neigh_table_clear(struct neigh_table *tbl)
 }
 EXPORT_SYMBOL(neigh_table_clear);
 
+static struct neigh_table *neigh_find_table(int family)
+{
+	struct neigh_table *tbl = NULL;
+
+	switch (family) {
+	case AF_INET:
+		tbl = neigh_tables[NEIGH_ARP_TABLE];
+		break;
+	case AF_INET6:
+		tbl = neigh_tables[NEIGH_ND_TABLE];
+		break;
+	case AF_DECnet:
+		tbl = neigh_tables[NEIGH_DN_TABLE];
+		break;
+	}
+
+	return tbl;
+}
+
 static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
 	struct nlattr *dst_attr;
 	struct neigh_table *tbl;
+	struct neighbour *neigh;
 	struct net_device *dev = NULL;
 	int err = -EINVAL;
 
@@ -1660,39 +1640,31 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
 		}
 	}
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
-		struct neighbour *neigh;
+	tbl = neigh_find_table(ndm->ndm_family);
+	if (tbl == NULL)
+		return -EAFNOSUPPORT;
 
-		if (tbl->family != ndm->ndm_family)
-			continue;
-		read_unlock(&neigh_tbl_lock);
-
-		if (nla_len(dst_attr) < tbl->key_len)
-			goto out;
-
-		if (ndm->ndm_flags & NTF_PROXY) {
-			err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
-			goto out;
-		}
+	if (nla_len(dst_attr) < tbl->key_len)
+		goto out;
 
-		if (dev == NULL)
-			goto out;
+	if (ndm->ndm_flags & NTF_PROXY) {
+		err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
+		goto out;
+	}
 
-		neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
-		if (neigh == NULL) {
-			err = -ENOENT;
-			goto out;
-		}
+	if (dev == NULL)
+		goto out;
 
-		err = neigh_update(neigh, NULL, NUD_FAILED,
-				   NEIGH_UPDATE_F_OVERRIDE |
-				   NEIGH_UPDATE_F_ADMIN);
-		neigh_release(neigh);
+	neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
+	if (neigh == NULL) {
+		err = -ENOENT;
 		goto out;
 	}
-	read_unlock(&neigh_tbl_lock);
-	err = -EAFNOSUPPORT;
+
+	err = neigh_update(neigh, NULL, NUD_FAILED,
+			   NEIGH_UPDATE_F_OVERRIDE |
+			   NEIGH_UPDATE_F_ADMIN);
+	neigh_release(neigh);
 
 out:
 	return err;
@@ -1700,11 +1672,14 @@ out:
 
 static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
+	int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
 	struct net *net = sock_net(skb->sk);
 	struct ndmsg *ndm;
 	struct nlattr *tb[NDA_MAX+1];
 	struct neigh_table *tbl;
 	struct net_device *dev = NULL;
+	struct neighbour *neigh;
+	void *dst, *lladdr;
 	int err;
 
 	ASSERT_RTNL();
@@ -1728,70 +1703,60 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
 			goto out;
 	}
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
-		int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
-		struct neighbour *neigh;
-		void *dst, *lladdr;
+	tbl = neigh_find_table(ndm->ndm_family);
+	if (tbl == NULL)
+		return -EAFNOSUPPORT;
 
-		if (tbl->family != ndm->ndm_family)
-			continue;
-		read_unlock(&neigh_tbl_lock);
+	if (nla_len(tb[NDA_DST]) < tbl->key_len)
+		goto out;
+	dst = nla_data(tb[NDA_DST]);
+	lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
 
-		if (nla_len(tb[NDA_DST]) < tbl->key_len)
-			goto out;
-		dst = nla_data(tb[NDA_DST]);
-		lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
+	if (ndm->ndm_flags & NTF_PROXY) {
+		struct pneigh_entry *pn;
 
-		if (ndm->ndm_flags & NTF_PROXY) {
-			struct pneigh_entry *pn;
+		err = -ENOBUFS;
+		pn = pneigh_lookup(tbl, net, dst, dev, 1);
+		if (pn) {
+			pn->flags = ndm->ndm_flags;
+			err = 0;
+		}
+		goto out;
+	}
 
-			err = -ENOBUFS;
-			pn = pneigh_lookup(tbl, net, dst, dev, 1);
-			if (pn) {
-				pn->flags = ndm->ndm_flags;
-				err = 0;
-			}
+	if (dev == NULL)
+		goto out;
+
+	neigh = neigh_lookup(tbl, dst, dev);
+	if (neigh == NULL) {
+		if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
+			err = -ENOENT;
 			goto out;
 		}
 
-		if (dev == NULL)
+		neigh = __neigh_lookup_errno(tbl, dst, dev);
+		if (IS_ERR(neigh)) {
+			err = PTR_ERR(neigh);
+			goto out;
+		}
+	} else {
+		if (nlh->nlmsg_flags & NLM_F_EXCL) {
+			err = -EEXIST;
+			neigh_release(neigh);
 			goto out;
-
-		neigh = neigh_lookup(tbl, dst, dev);
-		if (neigh == NULL) {
-			if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
-				err = -ENOENT;
-				goto out;
-			}
-
-			neigh = __neigh_lookup_errno(tbl, dst, dev);
-			if (IS_ERR(neigh)) {
-				err = PTR_ERR(neigh);
-				goto out;
-			}
-		} else {
-			if (nlh->nlmsg_flags & NLM_F_EXCL) {
-				err = -EEXIST;
-				neigh_release(neigh);
-				goto out;
-			}
-
-			if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
-				flags &= ~NEIGH_UPDATE_F_OVERRIDE;
 		}
 
-		if (ndm->ndm_flags & NTF_USE) {
-			neigh_event_send(neigh, NULL);
-			err = 0;
-		} else
-			err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
-		neigh_release(neigh);
-		goto out;
+		if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
+			flags &= ~NEIGH_UPDATE_F_OVERRIDE;
 	}
 
-	read_unlock(&neigh_tbl_lock);
-	err = -EAFNOSUPPORT;
+	if (ndm->ndm_flags & NTF_USE) {
+		neigh_event_send(neigh, NULL);
+		err = 0;
+	} else
+		err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+	neigh_release(neigh);
+
 out:
 	return err;
 }
@@ -1990,7 +1955,8 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct neigh_table *tbl;
 	struct ndtmsg *ndtmsg;
 	struct nlattr *tb[NDTA_MAX+1];
-	int err;
+	bool found = false;
+	int err, tidx;
 
 	err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
 			  nl_neightbl_policy);
@@ -2003,19 +1969,21 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 	}
 
 	ndtmsg = nlmsg_data(nlh);
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
+
+	for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
+		tbl = neigh_tables[tidx];
+		if (!tbl)
+			continue;
 		if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family)
 			continue;
-
-		if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0)
+		if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) {
+			found = true;
 			break;
+		}
 	}
 
-	if (tbl == NULL) {
-		err = -ENOENT;
-		goto errout_locked;
-	}
+	if (!found)
+		return -ENOENT;
 
 	/*
 	 * We acquire tbl->lock to be nice to the periodic timers and
@@ -2126,8 +2094,6 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 errout_tbl_lock:
 	write_unlock_bh(&tbl->lock);
-errout_locked:
-	read_unlock(&neigh_tbl_lock);
 errout:
 	return err;
 }
@@ -2142,10 +2108,13 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 
 	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
 
-	read_lock(&neigh_tbl_lock);
-	for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) {
+	for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
 		struct neigh_parms *p;
 
+		tbl = neigh_tables[tidx];
+		if (!tbl)
+			continue;
+
 		if (tidx < tbl_skip || (family && tbl->family != family))
 			continue;
 
@@ -2154,7 +2123,9 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 				       NLM_F_MULTI) <= 0)
 			break;
 
-		for (nidx = 0, p = tbl->parms.next; p; p = p->next) {
+		nidx = 0;
+		p = list_next_entry(&tbl->parms, list);
+		list_for_each_entry_from(p, &tbl->parms_list, list) {
 			if (!net_eq(neigh_parms_net(p), net))
 				continue;
 
@@ -2174,7 +2145,6 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 		neigh_skip = 0;
 	}
 out:
-	read_unlock(&neigh_tbl_lock);
 	cb->args[0] = tidx;
 	cb->args[1] = nidx;
 
@@ -2357,7 +2327,6 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 	int proxy = 0;
 	int err;
 
-	read_lock(&neigh_tbl_lock);
 	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
 
 	/* check for full ndmsg structure presence, family member is
@@ -2369,8 +2338,11 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 
 	s_t = cb->args[0];
 
-	for (tbl = neigh_tables, t = 0; tbl;
-	     tbl = tbl->next, t++) {
+	for (t = 0; t < NEIGH_NR_TABLES; t++) {
+		tbl = neigh_tables[t];
+
+		if (!tbl)
+			continue;
 		if (t < s_t || (family && tbl->family != family))
 			continue;
 		if (t > s_t)
@@ -2383,7 +2355,6 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
 		if (err < 0)
 			break;
 	}
-	read_unlock(&neigh_tbl_lock);
 
 	cb->args[0] = t;
 	return skb->len;