From 330c7272c40e965b8ab510d1022acd6e6a32e9c8 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 13 Feb 2018 08:52:00 -0800
Subject: net: Make dn_ptr depend on CONFIG_DECNET

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5eef6c8e2741..d2ef35e00626 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1800,7 +1800,9 @@ struct net_device {
 #endif
 	void 			*atalk_ptr;
 	struct in_device __rcu	*ip_ptr;
+#if IS_ENABLED(CONFIG_DECNET)
 	struct dn_dev __rcu     *dn_ptr;
+#endif
 	struct inet6_dev __rcu	*ip6_ptr;
 	void			*ax25_ptr;
 	struct wireless_dev	*ieee80211_ptr;
-- 
cgit v1.2.3


From 19ff13f2a411d99af67d8e51867d54b86e1bf017 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 13 Feb 2018 08:52:01 -0800
Subject: net: Make ax25_ptr depend on CONFIG_AX25

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 ++
 include/net/ax25.h        | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d2ef35e00626..936dc2c9dca1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1804,7 +1804,9 @@ struct net_device {
 	struct dn_dev __rcu     *dn_ptr;
 #endif
 	struct inet6_dev __rcu	*ip6_ptr;
+#if IS_ENABLED(CONFIG_AX25)
 	void			*ax25_ptr;
+#endif
 	struct wireless_dev	*ieee80211_ptr;
 	struct wpan_dev		*ieee802154_ptr;
 #if IS_ENABLED(CONFIG_MPLS_ROUTING)
diff --git a/include/net/ax25.h b/include/net/ax25.h
index 76fb39c272a7..c91bc87931c7 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -318,10 +318,12 @@ void ax25_digi_invert(const ax25_digi *, ax25_digi *);
 extern ax25_dev *ax25_dev_list;
 extern spinlock_t ax25_dev_lock;
 
+#if IS_ENABLED(CONFIG_AX25)
 static inline ax25_dev *ax25_dev_ax25dev(struct net_device *dev)
 {
 	return dev->ax25_ptr;
 }
+#endif
 
 ax25_dev *ax25_addr_ax25dev(ax25_address *);
 void ax25_dev_device_up(struct net_device *);
-- 
cgit v1.2.3


From 89e58148fbf2e4cbd84006e263061c19a2b47adf Mon Sep 17 00:00:00 2001
From: David Ahern <dsa@cumulusnetworks.com>
Date: Tue, 13 Feb 2018 08:52:02 -0800
Subject: net: Make atalk_ptr depend on ATALK or IRDA

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/atalk.h     | 2 ++
 include/linux/netdevice.h | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/atalk.h b/include/linux/atalk.h
index 4d356e168692..40373920ea58 100644
--- a/include/linux/atalk.h
+++ b/include/linux/atalk.h
@@ -113,10 +113,12 @@ extern void aarp_proto_init(void);
 /* Inter module exports */
 
 /* Give a device find its atif control structure */
+#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK)
 static inline struct atalk_iface *atalk_find_dev(struct net_device *dev)
 {
 	return dev->atalk_ptr;
 }
+#endif
 
 extern struct atalk_addr *atalk_find_dev_addr(struct net_device *dev);
 extern struct net_device *atrtr_get_dev(struct atalk_addr *sa);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 936dc2c9dca1..dbe6344b727a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1798,7 +1798,9 @@ struct net_device {
 #if IS_ENABLED(CONFIG_TIPC)
 	struct tipc_bearer __rcu *tipc_ptr;
 #endif
+#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK)
 	void 			*atalk_ptr;
+#endif
 	struct in_device __rcu	*ip_ptr;
 #if IS_ENABLED(CONFIG_DECNET)
 	struct dn_dev __rcu     *dn_ptr;
-- 
cgit v1.2.3


From 1ec54cb44e6731c3cb251bcf9251d65a4b4f6306 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 6 Mar 2018 10:56:31 +0100
Subject: net: unpollute priv_flags space

the ipvlan device driver defines and uses 2 bits inside the priv_flags
net_device field. Such bits and the related helper are used only
inside the ipvlan device driver, and the core networking does not
need to be aware of them.

This change moves netif_is_ipvlan* helper in the ipvlan driver and
re-implement them looking for ipvlan specific symbols instead of
using priv_flags.

Overall this frees two bits inside priv_flags - and move the following
ones to avoid gaps - without any intended functional change.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan.h      |  6 ++++++
 drivers/net/ipvlan/ipvlan_main.c | 10 ++++++----
 include/linux/netdevice.h        | 32 ++++++++------------------------
 3 files changed, 20 insertions(+), 28 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index a115f12bf130..c818b9bdab6e 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -177,4 +177,10 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 void ipvlan_link_delete(struct net_device *dev, struct list_head *head);
 void ipvlan_link_setup(struct net_device *dev);
 int ipvlan_link_register(struct rtnl_link_ops *ops);
+
+static inline bool netif_is_ipvlan_port(const struct net_device *dev)
+{
+	return dev->rx_handler == ipvlan_handle_frame;
+}
+
 #endif /* __IPVLAN_H */
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 4cbe9e27287d..23fd5ab180e8 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -129,7 +129,6 @@ static int ipvlan_port_create(struct net_device *dev)
 	if (err)
 		goto err;
 
-	dev->priv_flags |= IFF_IPVLAN_MASTER;
 	return 0;
 
 err:
@@ -142,7 +141,6 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	struct ipvl_port *port = ipvlan_port_get_rtnl(dev);
 	struct sk_buff *skb;
 
-	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
 	if (port->mode == IPVLAN_MODE_L3S) {
 		dev->priv_flags &= ~IFF_L3MDEV_MASTER;
 		ipvlan_unregister_nf_hook(dev_net(dev));
@@ -423,6 +421,12 @@ static const struct header_ops ipvlan_header_ops = {
 	.cache_update	= eth_header_cache_update,
 };
 
+static bool netif_is_ipvlan(const struct net_device *dev)
+{
+	/* both ipvlan and ipvtap devices use the same netdev_ops */
+	return dev->netdev_ops == &ipvlan_netdev_ops;
+}
+
 static int ipvlan_ethtool_get_link_ksettings(struct net_device *dev,
 					     struct ethtool_link_ksettings *cmd)
 {
@@ -600,8 +604,6 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	 */
 	memcpy(dev->dev_addr, phy_dev->dev_addr, ETH_ALEN);
 
-	dev->priv_flags |= IFF_IPVLAN_SLAVE;
-
 	err = register_netdevice(dev);
 	if (err < 0)
 		return err;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dbe6344b727a..95a613a7cc1c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1381,8 +1381,6 @@ struct net_device_ops {
  * @IFF_MACVLAN: Macvlan device
  * @IFF_XMIT_DST_RELEASE_PERM: IFF_XMIT_DST_RELEASE not taking into account
  *	underlying stacked devices
- * @IFF_IPVLAN_MASTER: IPvlan master device
- * @IFF_IPVLAN_SLAVE: IPvlan slave device
  * @IFF_L3MDEV_MASTER: device is an L3 master device
  * @IFF_NO_QUEUE: device can run without qdisc attached
  * @IFF_OPENVSWITCH: device is a Open vSwitch master
@@ -1412,16 +1410,14 @@ enum netdev_priv_flags {
 	IFF_LIVE_ADDR_CHANGE		= 1<<15,
 	IFF_MACVLAN			= 1<<16,
 	IFF_XMIT_DST_RELEASE_PERM	= 1<<17,
-	IFF_IPVLAN_MASTER		= 1<<18,
-	IFF_IPVLAN_SLAVE		= 1<<19,
-	IFF_L3MDEV_MASTER		= 1<<20,
-	IFF_NO_QUEUE			= 1<<21,
-	IFF_OPENVSWITCH			= 1<<22,
-	IFF_L3MDEV_SLAVE		= 1<<23,
-	IFF_TEAM			= 1<<24,
-	IFF_RXFH_CONFIGURED		= 1<<25,
-	IFF_PHONY_HEADROOM		= 1<<26,
-	IFF_MACSEC			= 1<<27,
+	IFF_L3MDEV_MASTER		= 1<<18,
+	IFF_NO_QUEUE			= 1<<19,
+	IFF_OPENVSWITCH			= 1<<20,
+	IFF_L3MDEV_SLAVE		= 1<<21,
+	IFF_TEAM			= 1<<22,
+	IFF_RXFH_CONFIGURED		= 1<<23,
+	IFF_PHONY_HEADROOM		= 1<<24,
+	IFF_MACSEC			= 1<<25,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1442,8 +1438,6 @@ enum netdev_priv_flags {
 #define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
 #define IFF_MACVLAN			IFF_MACVLAN
 #define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
-#define IFF_IPVLAN_MASTER		IFF_IPVLAN_MASTER
-#define IFF_IPVLAN_SLAVE		IFF_IPVLAN_SLAVE
 #define IFF_L3MDEV_MASTER		IFF_L3MDEV_MASTER
 #define IFF_NO_QUEUE			IFF_NO_QUEUE
 #define IFF_OPENVSWITCH			IFF_OPENVSWITCH
@@ -4223,16 +4217,6 @@ static inline bool netif_is_macvlan_port(const struct net_device *dev)
 	return dev->priv_flags & IFF_MACVLAN_PORT;
 }
 
-static inline bool netif_is_ipvlan(const struct net_device *dev)
-{
-	return dev->priv_flags & IFF_IPVLAN_SLAVE;
-}
-
-static inline bool netif_is_ipvlan_port(const struct net_device *dev)
-{
-	return dev->priv_flags & IFF_IPVLAN_MASTER;
-}
-
 static inline bool netif_is_bond_master(const struct net_device *dev)
 {
 	return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING;
-- 
cgit v1.2.3


From 79134e6ce2c9d1a00eab4d98cb48f975dd2474cb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 8 Mar 2018 12:51:41 -0800
Subject: net: do not create fallback tunnels for non-default namespaces

fallback tunnels (like tunl0, gre0, gretap0, erspan0, sit0,
ip6tnl0, ip6gre0) are automatically created when the corresponding
module is loaded.

These tunnels are also automatically created when a new network
namespace is created, at a great cost.

In many cases, netns are used for isolation purposes, and these
extra network devices are a waste of resources. We are using
thousands of netns per host, and hit the netns creation/delete
bottleneck a lot. (Many thanks to Kirill for recent work on this)

Add a new sysctl so that we can opt-out from this automatic creation.

Note that these tunnels are still created for the initial namespace,
to be the least intrusive for typical setups.

Tested:
lpk43:~# cat add_del_unshare.sh
for i in `seq 1 40`
do
 (for j in `seq 1 100` ; do  unshare -n /bin/true >/dev/null ; done) &
done
wait

lpk43:~# echo 0 >/proc/sys/net/core/fb_tunnels_only_for_init_net
lpk43:~# time ./add_del_unshare.sh

real	0m37.521s
user	0m0.886s
sys	7m7.084s
lpk43:~# echo 1 >/proc/sys/net/core/fb_tunnels_only_for_init_net
lpk43:~# time ./add_del_unshare.sh

real	0m4.761s
user	0m0.851s
sys	1m8.343s
lpk43:~#

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/sysctl/net.txt | 12 ++++++++++++
 include/linux/netdevice.h    |  7 +++++++
 include/net/ip_tunnels.h     |  2 ++
 net/core/sysctl_net_core.c   | 12 ++++++++++++
 net/ipv4/ip_tunnel.c         | 20 ++++++++++++--------
 net/ipv6/ip6_gre.c           |  4 +++-
 net/ipv6/ip6_tunnel.c        |  2 ++
 net/ipv6/sit.c               |  5 ++++-
 8 files changed, 54 insertions(+), 10 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 35c62f522754..5992602469d8 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -270,6 +270,18 @@ optmem_max
 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
 of struct cmsghdr structures with appended data.
 
+fb_tunnels_only_for_init_net
+----------------------------
+
+Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0,
+sit0, ip6tnl0, ip6gre0) are automatically created when a new
+network namespace is created, if corresponding tunnel is present
+in initial network namespace.
+If set to 1, these devices are not automatically created, and
+user space is responsible for creating them if needed.
+
+Default : 0  (for compatibility reasons)
+
 2. /proc/sys/net/unix - Parameters for Unix domain sockets
 -------------------------------------------------------
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 95a613a7cc1c..9711108c3916 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -585,6 +585,13 @@ struct netdev_queue {
 #endif
 } ____cacheline_aligned_in_smp;
 
+extern int sysctl_fb_tunnels_only_for_init_net;
+
+static inline bool net_has_fallback_tunnels(const struct net *net)
+{
+	return net == &init_net || !sysctl_fb_tunnels_only_for_init_net;
+}
+
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
 {
 #if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index cbe5addb9293..540a4b4417bf 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -180,8 +180,10 @@ struct tnl_ptk_info {
 
 struct ip_tunnel_net {
 	struct net_device *fb_tunnel_dev;
+	struct rtnl_link_ops *rtnl_link_ops;
 	struct hlist_head tunnels[IP_TNL_HASH_SIZE];
 	struct ip_tunnel __rcu *collect_md_tun;
+	int type;
 };
 
 static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index d714f65782b7..4f47f92459cc 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -32,6 +32,9 @@ static int max_skb_frags = MAX_SKB_FRAGS;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
+int sysctl_fb_tunnels_only_for_init_net __read_mostly = 0;
+EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net);
+
 #ifdef CONFIG_RPS
 static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -513,6 +516,15 @@ static struct ctl_table net_core_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 	},
+	{
+		.procname	= "fb_tunnels_only_for_init_net",
+		.data		= &sysctl_fb_tunnels_only_for_init_net,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 602597dfc395..5fcb17cb426b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -347,8 +347,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	struct net_device *dev;
 	int t_hlen;
 
-	BUG_ON(!itn->fb_tunnel_dev);
-	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
+	dev = __ip_tunnel_create(net, itn->rtnl_link_ops, parms);
 	if (IS_ERR(dev))
 		return ERR_CAST(dev);
 
@@ -822,7 +821,6 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 	struct net *net = t->net;
 	struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id);
 
-	BUG_ON(!itn->fb_tunnel_dev);
 	switch (cmd) {
 	case SIOCGETTUNNEL:
 		if (dev == itn->fb_tunnel_dev) {
@@ -847,7 +845,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 				p->o_key = 0;
 		}
 
-		t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
+		t = ip_tunnel_find(itn, p, itn->type);
 
 		if (cmd == SIOCADDTUNNEL) {
 			if (!t) {
@@ -991,10 +989,15 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 	struct ip_tunnel_parm parms;
 	unsigned int i;
 
+	itn->rtnl_link_ops = ops;
 	for (i = 0; i < IP_TNL_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&itn->tunnels[i]);
 
-	if (!ops) {
+	if (!ops || !net_has_fallback_tunnels(net)) {
+		struct ip_tunnel_net *it_init_net;
+
+		it_init_net = net_generic(&init_net, ip_tnl_net_id);
+		itn->type = it_init_net->type;
 		itn->fb_tunnel_dev = NULL;
 		return 0;
 	}
@@ -1012,6 +1015,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
 		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
+		itn->type = itn->fb_tunnel_dev->type;
 	}
 	rtnl_unlock();
 
@@ -1019,10 +1023,10 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
 
-static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
+static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn,
+			      struct list_head *head,
 			      struct rtnl_link_ops *ops)
 {
-	struct net *net = dev_net(itn->fb_tunnel_dev);
 	struct net_device *dev, *aux;
 	int h;
 
@@ -1054,7 +1058,7 @@ void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id,
 	rtnl_lock();
 	list_for_each_entry(net, net_list, exit_list) {
 		itn = net_generic(net, id);
-		ip_tunnel_destroy(itn, &list, ops);
+		ip_tunnel_destroy(net, itn, &list, ops);
 	}
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 18a3dfbd0300..7d8775c9570d 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -236,7 +236,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev,
 		return t;
 
 	dev = ign->fb_tunnel_dev;
-	if (dev->flags & IFF_UP)
+	if (dev && dev->flags & IFF_UP)
 		return netdev_priv(dev);
 
 	return NULL;
@@ -1472,6 +1472,8 @@ static int __net_init ip6gre_init_net(struct net *net)
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	int err;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
 	ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0",
 					  NET_NAME_UNKNOWN,
 					  ip6gre_tunnel_setup);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 56c4967f1868..5c045fa407da 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2205,6 +2205,8 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	ip6n->tnls[0] = ip6n->tnls_wc;
 	ip6n->tnls[1] = ip6n->tnls_r_l;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
 	err = -ENOMEM;
 	ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0",
 					NET_NAME_UNKNOWN, ip6_tnl_dev_setup);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a9c4ac6efe22..8a4f8fddd812 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -182,7 +182,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel *t = netdev_priv(dev);
 
-	if (dev == sitn->fb_tunnel_dev) {
+	if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) {
 		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
 		t->ip6rd.relay_prefix = 0;
 		t->ip6rd.prefixlen = 16;
@@ -1835,6 +1835,9 @@ static int __net_init sit_init_net(struct net *net)
 	sitn->tunnels[2] = sitn->tunnels_r;
 	sitn->tunnels[3] = sitn->tunnels_r_l;
 
+	if (!net_has_fallback_tunnels(net))
+		return 0;
+
 	sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
 					   NET_NAME_UNKNOWN,
 					   ipip6_tunnel_setup);
-- 
cgit v1.2.3


From f5426250a6ecfd1e9b2d5e0daf07565f664aa67d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 9 Mar 2018 10:39:24 +0100
Subject: net: introduce IFF_NO_RX_HANDLER

Some network devices - notably ipvlan slave - are not compatible with
any kind of rx_handler. Currently the hook can be installed but any
configuration (bridge, bond, macsec, ...) is nonfunctional.

This change allocates a priv_flag bit to mark such devices and explicitly
forbid installing a rx_handler if such bit is set. The new bit is used
by ipvlan slave device.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_main.c | 2 ++
 include/linux/netdevice.h        | 3 +++
 net/core/dev.c                   | 3 +++
 3 files changed, 8 insertions(+)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 23fd5ab180e8..743d37fb034a 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -604,6 +604,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev,
 	 */
 	memcpy(dev->dev_addr, phy_dev->dev_addr, ETH_ALEN);
 
+	dev->priv_flags |= IFF_NO_RX_HANDLER;
+
 	err = register_netdevice(dev);
 	if (err < 0)
 		return err;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9711108c3916..5fbb9f1da7fd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1397,6 +1397,7 @@ struct net_device_ops {
  * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external
  *	entity (i.e. the master device for bridged veth)
  * @IFF_MACSEC: device is a MACsec device
+ * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1425,6 +1426,7 @@ enum netdev_priv_flags {
 	IFF_RXFH_CONFIGURED		= 1<<23,
 	IFF_PHONY_HEADROOM		= 1<<24,
 	IFF_MACSEC			= 1<<25,
+	IFF_NO_RX_HANDLER		= 1<<26,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1452,6 +1454,7 @@ enum netdev_priv_flags {
 #define IFF_TEAM			IFF_TEAM
 #define IFF_RXFH_CONFIGURED		IFF_RXFH_CONFIGURED
 #define IFF_MACSEC			IFF_MACSEC
+#define IFF_NO_RX_HANDLER		IFF_NO_RX_HANDLER
 
 /**
  *	struct net_device - The DEVICE structure.
diff --git a/net/core/dev.c b/net/core/dev.c
index e5b8d42b6410..259abb1515d0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4351,6 +4351,9 @@ int netdev_rx_handler_register(struct net_device *dev,
 	if (netdev_is_rx_handler_busy(dev))
 		return -EBUSY;
 
+	if (dev->priv_flags & IFF_NO_RX_HANDLER)
+		return -EINVAL;
+
 	/* Note: rx_handler_data must be set before rx_handler */
 	rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
 	rcu_assign_pointer(dev->rx_handler, rx_handler);
-- 
cgit v1.2.3


From be9fc0971a5c27b791608cf9705a04fe96dbd395 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 13 Mar 2018 12:44:53 +0100
Subject: net: fix sysctl_fb_tunnels_only_for_init_net link error

The new variable is only available when CONFIG_SYSCTL is enabled,
otherwise we get a link error:

net/ipv4/ip_tunnel.o: In function `ip_tunnel_init_net':
ip_tunnel.c:(.text+0x278b): undefined reference to `sysctl_fb_tunnels_only_for_init_net'
net/ipv6/sit.o: In function `sit_init_net':
sit.c:(.init.text+0x4c): undefined reference to `sysctl_fb_tunnels_only_for_init_net'
net/ipv6/ip6_tunnel.o: In function `ip6_tnl_init_net':
ip6_tunnel.c:(.init.text+0x39): undefined reference to `sysctl_fb_tunnels_only_for_init_net'

This adds an extra condition, keeping the traditional behavior when
CONFIG_SYSCTL is disabled.

Fixes: 79134e6ce2c9 ("net: do not create fallback tunnels for non-default namespaces")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5fbb9f1da7fd..913b1cc882cf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -589,7 +589,9 @@ extern int sysctl_fb_tunnels_only_for_init_net;
 
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return net == &init_net || !sysctl_fb_tunnels_only_for_init_net;
+	return net == &init_net ||
+	       !IS_ENABLED(CONFIG_SYSCTL) ||
+	       !sysctl_fb_tunnels_only_for_init_net;
 }
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
-- 
cgit v1.2.3


From ede2762d93ff16e0974f7446516b46b1022db213 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Fri, 23 Mar 2018 19:47:19 +0300
Subject: net: Make NETDEV_XXX commands enum { }

This patch is preparation to drop NETDEV_UNREGISTER_FINAL.
Since the cmd is used in usnic_ib_netdev_event_to_string()
to get cmd name, after plain removing NETDEV_UNREGISTER_FINAL
from everywhere, we'd have holes in event2str[] in this
function.

Instead of that, let's make NETDEV_XXX commands names
available for everyone, and to define netdev_cmd_to_name()
in the way we won't have to shaffle names after their
numbers are changed.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/usnic/usnic_ib_main.c | 15 +------
 include/linux/netdevice.h                   | 69 +++++++++++++++--------------
 net/core/dev.c                              | 20 +++++++++
 3 files changed, 57 insertions(+), 47 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index f45e99a938e0..5bf3b20eba25 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -97,20 +97,7 @@ void usnic_ib_log_vf(struct usnic_ib_vf *vf)
 /* Start of netdev section */
 static inline const char *usnic_ib_netdev_event_to_string(unsigned long event)
 {
-	const char *event2str[] = {"NETDEV_NONE", "NETDEV_UP", "NETDEV_DOWN",
-		"NETDEV_REBOOT", "NETDEV_CHANGE",
-		"NETDEV_REGISTER", "NETDEV_UNREGISTER", "NETDEV_CHANGEMTU",
-		"NETDEV_CHANGEADDR", "NETDEV_GOING_DOWN", "NETDEV_FEAT_CHANGE",
-		"NETDEV_BONDING_FAILOVER", "NETDEV_PRE_UP",
-		"NETDEV_PRE_TYPE_CHANGE", "NETDEV_POST_TYPE_CHANGE",
-		"NETDEV_POST_INT", "NETDEV_UNREGISTER_FINAL", "NETDEV_RELEASE",
-		"NETDEV_NOTIFY_PEERS", "NETDEV_JOIN"
-	};
-
-	if (event >= ARRAY_SIZE(event2str))
-		return "UNKNOWN_NETDEV_EVENT";
-	else
-		return event2str[event];
+	return netdev_cmd_to_name(event);
 }
 
 static void usnic_ib_qp_grp_modify_active_to_err(struct usnic_ib_dev *us_ibdev)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 913b1cc882cf..dd5a04c971d5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2312,43 +2312,46 @@ struct netdev_lag_lower_state_info {
 
 #include <linux/notifier.h>
 
-/* netdevice notifier chain. Please remember to update the rtnetlink
- * notification exclusion list in rtnetlink_event() when adding new
- * types.
+/* netdevice notifier chain. Please remember to update netdev_cmd_to_name()
+ * and the rtnetlink notification exclusion list in rtnetlink_event() when
+ * adding new types.
  */
-#define NETDEV_UP	0x0001	/* For now you can't veto a device up/down */
-#define NETDEV_DOWN	0x0002
-#define NETDEV_REBOOT	0x0003	/* Tell a protocol stack a network interface
+enum netdev_cmd {
+	NETDEV_UP	= 1,	/* For now you can't veto a device up/down */
+	NETDEV_DOWN,
+	NETDEV_REBOOT,		/* Tell a protocol stack a network interface
 				   detected a hardware crash and restarted
 				   - we can use this eg to kick tcp sessions
 				   once done */
-#define NETDEV_CHANGE	0x0004	/* Notify device state change */
-#define NETDEV_REGISTER 0x0005
-#define NETDEV_UNREGISTER	0x0006
-#define NETDEV_CHANGEMTU	0x0007 /* notify after mtu change happened */
-#define NETDEV_CHANGEADDR	0x0008
-#define NETDEV_GOING_DOWN	0x0009
-#define NETDEV_CHANGENAME	0x000A
-#define NETDEV_FEAT_CHANGE	0x000B
-#define NETDEV_BONDING_FAILOVER 0x000C
-#define NETDEV_PRE_UP		0x000D
-#define NETDEV_PRE_TYPE_CHANGE	0x000E
-#define NETDEV_POST_TYPE_CHANGE	0x000F
-#define NETDEV_POST_INIT	0x0010
-#define NETDEV_UNREGISTER_FINAL 0x0011
-#define NETDEV_RELEASE		0x0012
-#define NETDEV_NOTIFY_PEERS	0x0013
-#define NETDEV_JOIN		0x0014
-#define NETDEV_CHANGEUPPER	0x0015
-#define NETDEV_RESEND_IGMP	0x0016
-#define NETDEV_PRECHANGEMTU	0x0017 /* notify before mtu change happened */
-#define NETDEV_CHANGEINFODATA	0x0018
-#define NETDEV_BONDING_INFO	0x0019
-#define NETDEV_PRECHANGEUPPER	0x001A
-#define NETDEV_CHANGELOWERSTATE	0x001B
-#define NETDEV_UDP_TUNNEL_PUSH_INFO	0x001C
-#define NETDEV_UDP_TUNNEL_DROP_INFO	0x001D
-#define NETDEV_CHANGE_TX_QUEUE_LEN	0x001E
+	NETDEV_CHANGE,		/* Notify device state change */
+	NETDEV_REGISTER,
+	NETDEV_UNREGISTER,
+	NETDEV_CHANGEMTU,	/* notify after mtu change happened */
+	NETDEV_CHANGEADDR,
+	NETDEV_GOING_DOWN,
+	NETDEV_CHANGENAME,
+	NETDEV_FEAT_CHANGE,
+	NETDEV_BONDING_FAILOVER,
+	NETDEV_PRE_UP,
+	NETDEV_PRE_TYPE_CHANGE,
+	NETDEV_POST_TYPE_CHANGE,
+	NETDEV_POST_INIT,
+	NETDEV_UNREGISTER_FINAL,
+	NETDEV_RELEASE,
+	NETDEV_NOTIFY_PEERS,
+	NETDEV_JOIN,
+	NETDEV_CHANGEUPPER,
+	NETDEV_RESEND_IGMP,
+	NETDEV_PRECHANGEMTU,	/* notify before mtu change happened */
+	NETDEV_CHANGEINFODATA,
+	NETDEV_BONDING_INFO,
+	NETDEV_PRECHANGEUPPER,
+	NETDEV_CHANGELOWERSTATE,
+	NETDEV_UDP_TUNNEL_PUSH_INFO,
+	NETDEV_UDP_TUNNEL_DROP_INFO,
+	NETDEV_CHANGE_TX_QUEUE_LEN,
+};
+const char *netdev_cmd_to_name(enum netdev_cmd cmd);
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
diff --git a/net/core/dev.c b/net/core/dev.c
index f9c28f44286c..055e7ae12759 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1571,6 +1571,26 @@ static void dev_disable_gro_hw(struct net_device *dev)
 		netdev_WARN(dev, "failed to disable GRO_HW!\n");
 }
 
+const char *netdev_cmd_to_name(enum netdev_cmd cmd)
+{
+#define N(val) 						\
+	case NETDEV_##val:				\
+		return "NETDEV_" __stringify(val);
+	switch (cmd) {
+	N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER)
+	N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE)
+	N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE)
+	N(POST_INIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER)
+	N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO)
+	N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO)
+	N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
+	N(UNREGISTER_FINAL)
+	};
+#undef N
+	return "UNKNOWN_NETDEV_EVENT";
+}
+EXPORT_SYMBOL_GPL(netdev_cmd_to_name);
+
 static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
 				   struct net_device *dev)
 {
-- 
cgit v1.2.3


From 070f2d7e264acd6316fc24092b7f51a18c75ac9c Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Fri, 23 Mar 2018 19:47:39 +0300
Subject: net: Drop NETDEV_UNREGISTER_FINAL

Last user is gone after bdf5bd7f2132 "rds: tcp: remove
register_netdevice_notifier infrastructure.", so we can
remove this netdevice command. This allows to delete
rtnl_lock() in netdev_run_todo(), which is hot path for
net namespace unregistration.

dev_change_net_namespace() and netdev_wait_allrefs()
have rcu_barrier() before NETDEV_UNREGISTER_FINAL call,
and the source commits say they were introduced to
delemit the call with NETDEV_UNREGISTER, but this patch
leaves them on the places, since they require additional
analysis, whether we need in them for something else.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/qedr/main.c | 4 ++--
 include/linux/netdevice.h         | 1 -
 include/rdma/ib_verbs.h           | 4 ++--
 net/core/dev.c                    | 7 -------
 4 files changed, 4 insertions(+), 12 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index db4bf97c0e15..eb32abb0099a 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -90,8 +90,8 @@ static struct net_device *qedr_get_netdev(struct ib_device *dev, u8 port_num)
 	dev_hold(qdev->ndev);
 
 	/* The HW vendor's device driver must guarantee
-	 * that this function returns NULL before the net device reaches
-	 * NETDEV_UNREGISTER_FINAL state.
+	 * that this function returns NULL before the net device has finished
+	 * NETDEV_UNREGISTER state.
 	 */
 	return qdev->ndev;
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dd5a04c971d5..2a2d9cf50aa2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2336,7 +2336,6 @@ enum netdev_cmd {
 	NETDEV_PRE_TYPE_CHANGE,
 	NETDEV_POST_TYPE_CHANGE,
 	NETDEV_POST_INIT,
-	NETDEV_UNREGISTER_FINAL,
 	NETDEV_RELEASE,
 	NETDEV_NOTIFY_PEERS,
 	NETDEV_JOIN,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index ff3ed435701f..6eb174753acf 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2122,8 +2122,8 @@ struct ib_device {
 	 * net device of device @device at port @port_num or NULL if such
 	 * a net device doesn't exist. The vendor driver should call dev_hold
 	 * on this net device. The HW vendor's device driver must guarantee
-	 * that this function returns NULL before the net device reaches
-	 * NETDEV_UNREGISTER_FINAL state.
+	 * that this function returns NULL before the net device has finished
+	 * NETDEV_UNREGISTER state.
 	 */
 	struct net_device	  *(*get_netdev)(struct ib_device *device,
 						 u8 port_num);
diff --git a/net/core/dev.c b/net/core/dev.c
index 055e7ae12759..97a96df4b6da 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1584,7 +1584,6 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
 	N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO)
 	N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO)
 	N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
-	N(UNREGISTER_FINAL)
 	};
 #undef N
 	return "UNKNOWN_NETDEV_EVENT";
@@ -8097,7 +8096,6 @@ static void netdev_wait_allrefs(struct net_device *dev)
 			rcu_barrier();
 			rtnl_lock();
 
-			call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
 			if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
 				     &dev->state)) {
 				/* We must not have linkwatch events
@@ -8169,10 +8167,6 @@ void netdev_run_todo(void)
 			= list_first_entry(&list, struct net_device, todo_list);
 		list_del(&dev->todo_list);
 
-		rtnl_lock();
-		call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
-		__rtnl_unlock();
-
 		if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) {
 			pr_err("network todo '%s' but state %d\n",
 			       dev->name, dev->reg_state);
@@ -8614,7 +8608,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	 */
 	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 	rcu_barrier();
-	call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
 
 	new_nsid = peernet2id_alloc(dev_net(dev), net);
 	/* If there is an ifindex conflict assign a new one */
-- 
cgit v1.2.3


From 9daae9bd47cff82a2a06aca23c458d6c79d09d52 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 28 Mar 2018 17:46:54 +0300
Subject: net: Call add/kill vid ndo on vlan filter feature toggling

NETIF_F_HW_VLAN_[CS]TAG_FILTER features require more than just a bit
flip in dev->features in order to keep the driver in a consistent state.
These features notify the driver of each added/removed vlan, but toggling
of vlan-filter does not notify the driver accordingly for each of the
existing vlans.

This patch implements a similar solution to NETIF_F_RX_UDP_TUNNEL_PORT
behavior (which notifies the driver about UDP ports in the same manner
that vids are reported).

Each toggling of the features propagates to the 8021q module, which
iterates over the vlans and call add/kill ndo accordingly.

Signed-off-by: Gal Pressman <galp@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h   |  24 +++++++++++
 include/linux/netdevice.h |   4 ++
 net/8021q/vlan.c          |  21 ++++++++++
 net/8021q/vlan.h          |   3 ++
 net/8021q/vlan_core.c     | 101 ++++++++++++++++++++++++++++++++++------------
 net/core/dev.c            |  20 +++++++++
 6 files changed, 148 insertions(+), 25 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index c4a1cff9c768..24d1976c1e61 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -83,6 +83,30 @@ static inline bool is_vlan_dev(const struct net_device *dev)
 #define skb_vlan_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
 #define skb_vlan_tag_get_prio(__skb)	((__skb)->vlan_tci & VLAN_PRIO_MASK)
 
+static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	return notifier_to_errno(call_netdevice_notifiers(NETDEV_CVLAN_FILTER_PUSH_INFO, dev));
+}
+
+static inline void vlan_drop_rx_ctag_filter_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	call_netdevice_notifiers(NETDEV_CVLAN_FILTER_DROP_INFO, dev);
+}
+
+static inline int vlan_get_rx_stag_filter_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	return notifier_to_errno(call_netdevice_notifiers(NETDEV_SVLAN_FILTER_PUSH_INFO, dev));
+}
+
+static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	call_netdevice_notifiers(NETDEV_SVLAN_FILTER_DROP_INFO, dev);
+}
+
 /**
  *	struct vlan_pcpu_stats - VLAN percpu rx/tx stats
  *	@rx_packets: number of received packets
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2a2d9cf50aa2..da44dab492e3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2349,6 +2349,10 @@ enum netdev_cmd {
 	NETDEV_UDP_TUNNEL_PUSH_INFO,
 	NETDEV_UDP_TUNNEL_DROP_INFO,
 	NETDEV_CHANGE_TX_QUEUE_LEN,
+	NETDEV_CVLAN_FILTER_PUSH_INFO,
+	NETDEV_CVLAN_FILTER_DROP_INFO,
+	NETDEV_SVLAN_FILTER_PUSH_INFO,
+	NETDEV_SVLAN_FILTER_DROP_INFO,
 };
 const char *netdev_cmd_to_name(enum netdev_cmd cmd);
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index bad01b14a4ad..5505ee6ebdbe 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -360,6 +360,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 	struct vlan_dev_priv *vlan;
 	bool last = false;
 	LIST_HEAD(list);
+	int err;
 
 	if (is_vlan_dev(dev)) {
 		int err = __vlan_device_event(dev, event);
@@ -489,6 +490,26 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 		vlan_group_for_each_dev(grp, i, vlandev)
 			call_netdevice_notifiers(event, vlandev);
 		break;
+
+	case NETDEV_CVLAN_FILTER_PUSH_INFO:
+		err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021Q));
+		if (err)
+			return notifier_from_errno(err);
+		break;
+
+	case NETDEV_CVLAN_FILTER_DROP_INFO:
+		vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021Q));
+		break;
+
+	case NETDEV_SVLAN_FILTER_PUSH_INFO:
+		err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021AD));
+		if (err)
+			return notifier_from_errno(err);
+		break;
+
+	case NETDEV_SVLAN_FILTER_DROP_INFO:
+		vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021AD));
+		break;
 	}
 
 out:
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index a8ba51030b75..e23aac3e4d37 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -97,6 +97,9 @@ static inline struct net_device *vlan_find_dev(struct net_device *real_dev,
 		if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \
 							    (i) % VLAN_N_VID)))
 
+int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto);
+void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto);
+
 /* found in vlan_dev.c */
 void vlan_dev_set_ingress_priority(const struct net_device *dev,
 				   u32 skb_prio, u16 vlan_prio);
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 45c9bf5ff3a0..c8d7abdc0463 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -165,13 +165,12 @@ struct vlan_vid_info {
 	int refcount;
 };
 
-static bool vlan_hw_filter_capable(const struct net_device *dev,
-				     const struct vlan_vid_info *vid_info)
+bool vlan_hw_filter_capable(const struct net_device *dev, __be16 proto)
 {
-	if (vid_info->proto == htons(ETH_P_8021Q) &&
+	if (proto == htons(ETH_P_8021Q) &&
 	    dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
 		return true;
-	if (vid_info->proto == htons(ETH_P_8021AD) &&
+	if (proto == htons(ETH_P_8021AD) &&
 	    dev->features & NETIF_F_HW_VLAN_STAG_FILTER)
 		return true;
 	return false;
@@ -202,11 +201,73 @@ static struct vlan_vid_info *vlan_vid_info_alloc(__be16 proto, u16 vid)
 	return vid_info;
 }
 
+static int vlan_add_rx_filter_info(struct net_device *dev, __be16 proto, u16 vid)
+{
+	if (!vlan_hw_filter_capable(dev, proto))
+		return 0;
+
+	if (netif_device_present(dev))
+		return dev->netdev_ops->ndo_vlan_rx_add_vid(dev, proto, vid);
+	else
+		return -ENODEV;
+}
+
+static int vlan_kill_rx_filter_info(struct net_device *dev, __be16 proto, u16 vid)
+{
+	if (!vlan_hw_filter_capable(dev, proto))
+		return 0;
+
+	if (netif_device_present(dev))
+		return dev->netdev_ops->ndo_vlan_rx_kill_vid(dev, proto, vid);
+	else
+		return -ENODEV;
+}
+
+int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto)
+{
+	struct net_device *real_dev = vlan_info->real_dev;
+	struct vlan_vid_info *vlan_vid_info;
+	int err;
+
+	list_for_each_entry(vlan_vid_info, &vlan_info->vid_list, list) {
+		if (vlan_vid_info->proto == proto) {
+			err = vlan_add_rx_filter_info(real_dev, proto,
+						      vlan_vid_info->vid);
+			if (err)
+				goto unwind;
+		}
+	}
+
+	return 0;
+
+unwind:
+	list_for_each_entry_continue_reverse(vlan_vid_info,
+					     &vlan_info->vid_list, list) {
+		if (vlan_vid_info->proto == proto)
+			vlan_kill_rx_filter_info(real_dev, proto,
+						 vlan_vid_info->vid);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(vlan_filter_push_vids);
+
+void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto)
+{
+	struct vlan_vid_info *vlan_vid_info;
+
+	list_for_each_entry(vlan_vid_info, &vlan_info->vid_list, list)
+		if (vlan_vid_info->proto == proto)
+			vlan_kill_rx_filter_info(vlan_info->real_dev,
+						 vlan_vid_info->proto,
+						 vlan_vid_info->vid);
+}
+EXPORT_SYMBOL(vlan_filter_drop_vids);
+
 static int __vlan_vid_add(struct vlan_info *vlan_info, __be16 proto, u16 vid,
 			  struct vlan_vid_info **pvid_info)
 {
 	struct net_device *dev = vlan_info->real_dev;
-	const struct net_device_ops *ops = dev->netdev_ops;
 	struct vlan_vid_info *vid_info;
 	int err;
 
@@ -214,16 +275,12 @@ static int __vlan_vid_add(struct vlan_info *vlan_info, __be16 proto, u16 vid,
 	if (!vid_info)
 		return -ENOMEM;
 
-	if (vlan_hw_filter_capable(dev, vid_info)) {
-		if (netif_device_present(dev))
-			err = ops->ndo_vlan_rx_add_vid(dev, proto, vid);
-		else
-			err = -ENODEV;
-		if (err) {
-			kfree(vid_info);
-			return err;
-		}
+	err = vlan_add_rx_filter_info(dev, proto, vid);
+	if (err) {
+		kfree(vid_info);
+		return err;
 	}
+
 	list_add(&vid_info->list, &vlan_info->vid_list);
 	vlan_info->nr_vids++;
 	*pvid_info = vid_info;
@@ -270,21 +327,15 @@ static void __vlan_vid_del(struct vlan_info *vlan_info,
 			   struct vlan_vid_info *vid_info)
 {
 	struct net_device *dev = vlan_info->real_dev;
-	const struct net_device_ops *ops = dev->netdev_ops;
 	__be16 proto = vid_info->proto;
 	u16 vid = vid_info->vid;
 	int err;
 
-	if (vlan_hw_filter_capable(dev, vid_info)) {
-		if (netif_device_present(dev))
-			err = ops->ndo_vlan_rx_kill_vid(dev, proto, vid);
-		else
-			err = -ENODEV;
-		if (err) {
-			pr_warn("failed to kill vid %04x/%d for device %s\n",
-				proto, vid, dev->name);
-		}
-	}
+	err = vlan_kill_rx_filter_info(dev, proto, vid);
+	if (err)
+		pr_warn("failed to kill vid %04x/%d for device %s\n",
+			proto, vid, dev->name);
+
 	list_del(&vid_info->list);
 	kfree(vid_info);
 	vlan_info->nr_vids--;
diff --git a/net/core/dev.c b/net/core/dev.c
index eca5458b2753..1ddb6b9c58a8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1584,6 +1584,8 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
 	N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO)
 	N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO)
 	N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
+	N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
+	N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
 	};
 #undef N
 	return "UNKNOWN_NETDEV_EVENT";
@@ -7665,6 +7667,24 @@ sync_lower:
 			}
 		}
 
+		if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) {
+			if (features & NETIF_F_HW_VLAN_CTAG_FILTER) {
+				dev->features = features;
+				err |= vlan_get_rx_ctag_filter_info(dev);
+			} else {
+				vlan_drop_rx_ctag_filter_info(dev);
+			}
+		}
+
+		if (diff & NETIF_F_HW_VLAN_STAG_FILTER) {
+			if (features & NETIF_F_HW_VLAN_STAG_FILTER) {
+				dev->features = features;
+				err |= vlan_get_rx_stag_filter_info(dev);
+			} else {
+				vlan_drop_rx_stag_filter_info(dev);
+			}
+		}
+
 		dev->features = features;
 	}
 
-- 
cgit v1.2.3


From e679c9c1dbfdba07b2a979a076cca74b773be8ce Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 28 Mar 2018 15:44:16 -0700
Subject: sfp/phylink: move module EEPROM ethtool access into netdev core
 ethtool

Provide a pointer to the SFP bus in struct net_device, so that the
ethtool module EEPROM methods can access the SFP directly, rather
than needing every user to provide a hook for it.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 18 ------------------
 drivers/net/phy/phylink.c             | 28 ----------------------------
 drivers/net/phy/sfp-bus.c             |  6 ++----
 include/linux/netdevice.h             |  3 +++
 include/linux/phylink.h               |  3 ---
 net/core/ethtool.c                    |  7 +++++++
 6 files changed, 12 insertions(+), 53 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index cd09bde55596..25ced96750bf 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4075,22 +4075,6 @@ static int mvneta_ethtool_set_wol(struct net_device *dev,
 	return ret;
 }
 
-static int mvneta_ethtool_get_module_info(struct net_device *dev,
-					  struct ethtool_modinfo *modinfo)
-{
-	struct mvneta_port *pp = netdev_priv(dev);
-
-	return phylink_ethtool_get_module_info(pp->phylink, modinfo);
-}
-
-static int mvneta_ethtool_get_module_eeprom(struct net_device *dev,
-					    struct ethtool_eeprom *ee, u8 *buf)
-{
-	struct mvneta_port *pp = netdev_priv(dev);
-
-	return phylink_ethtool_get_module_eeprom(pp->phylink, ee, buf);
-}
-
 static int mvneta_ethtool_get_eee(struct net_device *dev,
 				  struct ethtool_eee *eee)
 {
@@ -4165,8 +4149,6 @@ static const struct ethtool_ops mvneta_eth_tool_ops = {
 	.set_link_ksettings = mvneta_ethtool_set_link_ksettings,
 	.get_wol        = mvneta_ethtool_get_wol,
 	.set_wol        = mvneta_ethtool_set_wol,
-	.get_module_info = mvneta_ethtool_get_module_info,
-	.get_module_eeprom = mvneta_ethtool_get_module_eeprom,
 	.get_eee	= mvneta_ethtool_get_eee,
 	.set_eee	= mvneta_ethtool_set_eee,
 };
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 9b1e4721ea3a..c582b2d7546c 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1250,34 +1250,6 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl,
 }
 EXPORT_SYMBOL_GPL(phylink_ethtool_set_pauseparam);
 
-int phylink_ethtool_get_module_info(struct phylink *pl,
-				    struct ethtool_modinfo *modinfo)
-{
-	int ret = -EOPNOTSUPP;
-
-	WARN_ON(!lockdep_rtnl_is_held());
-
-	if (pl->sfp_bus)
-		ret = sfp_get_module_info(pl->sfp_bus, modinfo);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(phylink_ethtool_get_module_info);
-
-int phylink_ethtool_get_module_eeprom(struct phylink *pl,
-				      struct ethtool_eeprom *ee, u8 *buf)
-{
-	int ret = -EOPNOTSUPP;
-
-	WARN_ON(!lockdep_rtnl_is_held());
-
-	if (pl->sfp_bus)
-		ret = sfp_get_module_eeprom(pl->sfp_bus, ee, buf);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(phylink_ethtool_get_module_eeprom);
-
 /**
  * phylink_ethtool_get_eee_err() - read the energy efficient ethernet error
  *   counter
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 3d4ff5d0d2a6..0381da78d228 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -342,6 +342,7 @@ static int sfp_register_bus(struct sfp_bus *bus)
 	}
 	if (bus->started)
 		bus->socket_ops->start(bus->sfp);
+	bus->netdev->sfp_bus = bus;
 	bus->registered = true;
 	return 0;
 }
@@ -356,6 +357,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 		if (bus->phydev && ops && ops->disconnect_phy)
 			ops->disconnect_phy(bus->upstream);
 	}
+	bus->netdev->sfp_bus = NULL;
 	bus->registered = false;
 }
 
@@ -371,8 +373,6 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
  */
 int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo)
 {
-	if (!bus->registered)
-		return -ENOIOCTLCMD;
 	return bus->socket_ops->module_info(bus->sfp, modinfo);
 }
 EXPORT_SYMBOL_GPL(sfp_get_module_info);
@@ -391,8 +391,6 @@ EXPORT_SYMBOL_GPL(sfp_get_module_info);
 int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee,
 			  u8 *data)
 {
-	if (!bus->registered)
-		return -ENOIOCTLCMD;
 	return bus->socket_ops->module_eeprom(bus->sfp, ee, data);
 }
 EXPORT_SYMBOL_GPL(sfp_get_module_eeprom);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index da44dab492e3..cf44503ea81a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -58,6 +58,7 @@ struct device;
 struct phy_device;
 struct dsa_port;
 
+struct sfp_bus;
 /* 802.11 specific */
 struct wireless_dev;
 /* 802.15.4 specific */
@@ -1662,6 +1663,7 @@ enum netdev_priv_flags {
  *	@priomap:	XXX: need comments on this one
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
+ *	@sfp_bus:	attached &struct sfp_bus structure.
  *
  *	@qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
  *	@qdisc_running_key: lockdep class annotating Qdisc->running seqcount
@@ -1945,6 +1947,7 @@ struct net_device {
 	struct netprio_map __rcu *priomap;
 #endif
 	struct phy_device	*phydev;
+	struct sfp_bus		*sfp_bus;
 	struct lock_class_key	*qdisc_tx_busylock;
 	struct lock_class_key	*qdisc_running_key;
 	bool			proto_down;
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index e95cc12030fa..50eeae025f1e 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -219,9 +219,6 @@ void phylink_ethtool_get_pauseparam(struct phylink *,
 				    struct ethtool_pauseparam *);
 int phylink_ethtool_set_pauseparam(struct phylink *,
 				   struct ethtool_pauseparam *);
-int phylink_ethtool_get_module_info(struct phylink *, struct ethtool_modinfo *);
-int phylink_ethtool_get_module_eeprom(struct phylink *,
-				      struct ethtool_eeprom *, u8 *);
 int phylink_get_eee_err(struct phylink *);
 int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *);
 int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index bb6e498c6e3d..eb55252ca1fb 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -22,6 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
+#include <linux/sfp.h>
 #include <linux/slab.h>
 #include <linux/rtnetlink.h>
 #include <linux/sched/signal.h>
@@ -2245,6 +2246,9 @@ static int __ethtool_get_module_info(struct net_device *dev,
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct phy_device *phydev = dev->phydev;
 
+	if (dev->sfp_bus)
+		return sfp_get_module_info(dev->sfp_bus, modinfo);
+
 	if (phydev && phydev->drv && phydev->drv->module_info)
 		return phydev->drv->module_info(phydev, modinfo);
 
@@ -2279,6 +2283,9 @@ static int __ethtool_get_module_eeprom(struct net_device *dev,
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct phy_device *phydev = dev->phydev;
 
+	if (dev->sfp_bus)
+		return sfp_get_module_eeprom(dev->sfp_bus, ee, data);
+
 	if (phydev && phydev->drv && phydev->drv->module_eeprom)
 		return phydev->drv->module_eeprom(phydev, ee, data);
 
-- 
cgit v1.2.3