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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

2 files changed, 54 insertions, 26 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 84a4e4c3be4b..2ad445c1d27c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -65,6 +65,7 @@
 #include <linux/net_namespace.h>
 
 #include <net/net_namespace.h>
+#include <net/netns/generic.h>
 #include <net/sock.h>
 #include <net/scm.h>
 #include <net/netlink.h>
@@ -145,8 +146,6 @@ static atomic_t nl_table_users = ATOMIC_INIT(0);
 
 static BLOCKING_NOTIFIER_HEAD(netlink_chain);
 
-static DEFINE_SPINLOCK(netlink_tap_lock);
-static struct list_head netlink_tap_all __read_mostly;
 
 static const struct rhashtable_params netlink_rhashtable_params;
 
@@ -173,14 +172,24 @@ static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
 	return new;
 }
 
+static unsigned int netlink_tap_net_id;
+
+struct netlink_tap_net {
+	struct list_head netlink_tap_all;
+	struct mutex netlink_tap_lock;
+};
+
 int netlink_add_tap(struct netlink_tap *nt)
 {
+	struct net *net = dev_net(nt->dev);
+	struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
+
 	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
 		return -EINVAL;
 
-	spin_lock(&netlink_tap_lock);
-	list_add_rcu(&nt->list, &netlink_tap_all);
-	spin_unlock(&netlink_tap_lock);
+	mutex_lock(&nn->netlink_tap_lock);
+	list_add_rcu(&nt->list, &nn->netlink_tap_all);
+	mutex_unlock(&nn->netlink_tap_lock);
 
 	__module_get(nt->module);
 
@@ -190,12 +199,14 @@ EXPORT_SYMBOL_GPL(netlink_add_tap);
 
 static int __netlink_remove_tap(struct netlink_tap *nt)
 {
+	struct net *net = dev_net(nt->dev);
+	struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
 	bool found = false;
 	struct netlink_tap *tmp;
 
-	spin_lock(&netlink_tap_lock);
+	mutex_lock(&nn->netlink_tap_lock);
 
-	list_for_each_entry(tmp, &netlink_tap_all, list) {
+	list_for_each_entry(tmp, &nn->netlink_tap_all, list) {
 		if (nt == tmp) {
 			list_del_rcu(&nt->list);
 			found = true;
@@ -205,7 +216,7 @@ static int __netlink_remove_tap(struct netlink_tap *nt)
 
 	pr_warn("__netlink_remove_tap: %p not found\n", nt);
 out:
-	spin_unlock(&netlink_tap_lock);
+	mutex_unlock(&nn->netlink_tap_lock);
 
 	if (found)
 		module_put(nt->module);
@@ -224,6 +235,26 @@ int netlink_remove_tap(struct netlink_tap *nt)
 }
 EXPORT_SYMBOL_GPL(netlink_remove_tap);
 
+static __net_init int netlink_tap_init_net(struct net *net)
+{
+	struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
+
+	INIT_LIST_HEAD(&nn->netlink_tap_all);
+	mutex_init(&nn->netlink_tap_lock);
+	return 0;
+}
+
+static void __net_exit netlink_tap_exit_net(struct net *net)
+{
+}
+
+static struct pernet_operations netlink_tap_net_ops = {
+	.init = netlink_tap_init_net,
+	.exit = netlink_tap_exit_net,
+	.id   = &netlink_tap_net_id,
+	.size = sizeof(struct netlink_tap_net),
+};
+
 static bool netlink_filter_tap(const struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
@@ -277,7 +308,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	return ret;
 }
 
-static void __netlink_deliver_tap(struct sk_buff *skb)
+static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn)
 {
 	int ret;
 	struct netlink_tap *tmp;
@@ -285,19 +316,21 @@ static void __netlink_deliver_tap(struct sk_buff *skb)
 	if (!netlink_filter_tap(skb))
 		return;
 
-	list_for_each_entry_rcu(tmp, &netlink_tap_all, list) {
+	list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) {
 		ret = __netlink_deliver_tap_skb(skb, tmp->dev);
 		if (unlikely(ret))
 			break;
 	}
 }
 
-static void netlink_deliver_tap(struct sk_buff *skb)
+static void netlink_deliver_tap(struct net *net, struct sk_buff *skb)
 {
+	struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id);
+
 	rcu_read_lock();
 
-	if (unlikely(!list_empty(&netlink_tap_all)))
-		__netlink_deliver_tap(skb);
+	if (unlikely(!list_empty(&nn->netlink_tap_all)))
+		__netlink_deliver_tap(skb, nn);
 
 	rcu_read_unlock();
 }
@@ -306,7 +339,7 @@ static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src,
 				       struct sk_buff *skb)
 {
 	if (!(netlink_is_kernel(dst) && netlink_is_kernel(src)))
-		netlink_deliver_tap(skb);
+		netlink_deliver_tap(sock_net(dst), skb);
 }
 
 static void netlink_overrun(struct sock *sk)
@@ -1216,7 +1249,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 {
 	int len = skb->len;
 
-	netlink_deliver_tap(skb);
+	netlink_deliver_tap(sock_net(sk), skb);
 
 	skb_queue_tail(&sk->sk_receive_queue, skb);
 	sk->sk_data_ready(sk);
@@ -2482,8 +2515,9 @@ static int netlink_walk_start(struct nl_seq_iter *iter)
 		return err;
 	}
 
-	err = rhashtable_walk_start(&iter->hti);
-	return err == -EAGAIN ? 0 : err;
+	rhashtable_walk_start(&iter->hti);
+
+	return 0;
 }
 
 static void netlink_walk_stop(struct nl_seq_iter *iter)
@@ -2604,7 +2638,6 @@ static int netlink_seq_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations netlink_seq_fops = {
-	.owner		= THIS_MODULE,
 	.open		= netlink_seq_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -2734,12 +2767,11 @@ static int __init netlink_proto_init(void)
 		}
 	}
 
-	INIT_LIST_HEAD(&netlink_tap_all);
-
 	netlink_add_usersock_entry();
 
 	sock_register(&netlink_family_ops);
 	register_pernet_subsys(&netlink_net_ops);
+	register_pernet_subsys(&netlink_tap_net_ops);
 	/* The netlink device handler may be needed early. */
 	rtnetlink_init();
 out:
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 8faa20b4d457..7dda33b9b784 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -115,11 +115,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	if (!s_num)
 		rhashtable_walk_enter(&tbl->hash, hti);
 
-	ret = rhashtable_walk_start(hti);
-	if (ret == -EAGAIN)
-		ret = 0;
-	if (ret)
-		goto stop;
+	rhashtable_walk_start(hti);
 
 	while ((nlsk = rhashtable_walk_next(hti))) {
 		if (IS_ERR(nlsk)) {
@@ -146,8 +142,8 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		}
 	}
 
-stop:
 	rhashtable_walk_stop(hti);
+
 	if (ret)
 		goto done;