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

Pull networking fixes from David Miller:

 1) In TCP, don't register an FRTO for cumulatively ACK'd data that was
    previously SACK'd, from Neal Cardwell.

 2) Need to hold RNL mutex in ipv4 multicast code namespace cleanup,
    from Cong WANG.

 3) Similarly we have to hold RNL mutex for fib_rules_unregister(), also
    from Cong WANG.

 4) Revert and rework netns nsid allocation fix, from Nicolas Dichtel.

 5) When we encapsulate for a tunnel device, skb->sk still points to the
    user socket.  So this leads to cases where we retraverse the
    ipv4/ipv6 output path with skb->sk being of some other address
    family (f.e. AF_PACKET).  This can cause things to crash since the
    ipv4 output path is dereferencing an AF_PACKET socket as if it were
    an ipv4 one.

    The short term fix for 'net' and -stable is to elide these socket
    checks once we've entered an encapsulation sequence by testing
    xmit_recursion.

    Longer term we have a better solution wherein we pass the tunnel's
    socket down through the output paths, but that is way too invasive
    for 'net' and -stable.

    From Hannes Frederic Sowa.

 6) l2tp_init() failure path forgets to unregister per-net ops, from
    Cong WANG.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  net/mlx4_core: Fix error message deprecation for ConnectX-2 cards
  net: dsa: fix filling routing table from OF description
  l2tp: unregister l2tp_net_ops on failure path
  mvneta: dont call mvneta_adjust_link() manually
  ipv6: protect skb->sk accesses from recursive dereference inside the stack
  netns: don't allocate an id for dead netns
  Revert "netns: don't clear nsid too early on removal"
  ip6mr: call del_timer_sync() in ip6mr_free_table()
  net: move fib_rules_unregister() under rtnl lock
  ipv4: take rtnl_lock and mark mrt table as freed on namespace cleanup
  tcp: fix FRTO undo on cumulative ACK of SACKed range
  xen-netfront: transmit fully GSO-sized packets

21 files changed, 78 insertions, 71 deletions

diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index e124847443f8..f0b4cd72411d 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -19,7 +19,9 @@ the parent DSA node. The maximum number of allowed child nodes is 4
 (DSA_MAX_SWITCHES).
 Each of these switch child nodes should have the following required properties:
 
-- reg                   : Describes the switch address on the MII bus
+- reg                   : Contains two fields. The first one describes the
+                          address on the MII bus. The second is the switch
+                          number that must be unique in cascaded configurations
 - #address-cells        : Must be 1
 - #size-cells           : Must be 0
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 96208f17bb53..2db653225a0e 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2658,16 +2658,11 @@ static int mvneta_stop(struct net_device *dev)
 static int mvneta_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
         struct mvneta_port *pp = netdev_priv(dev);
-        int ret;
 
         if (!pp->phy_dev)
                 return -ENOTSUPP;
 
-        ret = phy_mii_ioctl(pp->phy_dev, ifr, cmd);
-        if (!ret)
-                mvneta_adjust_link(dev);
-
-        return ret;
+        return phy_mii_ioctl(pp->phy_dev, ifr, cmd);
 }
 
 /* Ethtool methods */
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 3350721bf515..546ca4226916 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -724,7 +724,8 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
                  * on the host, we deprecate the error message for this
                  * specific command/input_mod/opcode_mod/fw-status to be debug.
                  */
-                if (op == MLX4_CMD_SET_PORT && in_modifier == 1 &&
+                if (op == MLX4_CMD_SET_PORT &&
+                    (in_modifier == 1 || in_modifier == 2) &&
                     op_modifier == 0 && context->fw_status == CMD_STAT_BAD_SIZE)
                         mlx4_dbg(dev, "command 0x%x failed: fw status = 0x%x\n",
                                  op, context->fw_status);
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index e9b960f0ff32..720aaf6313d2 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1008,8 +1008,7 @@ err:
 
 static int xennet_change_mtu(struct net_device *dev, int mtu)
 {
-        int max = xennet_can_sg(dev) ?
-                XEN_NETIF_MAX_TX_SIZE - MAX_TCP_HEADER : ETH_DATA_LEN;
+        int max = xennet_can_sg(dev) ? XEN_NETIF_MAX_TX_SIZE : ETH_DATA_LEN;
 
         if (mtu > max)
                 return -EINVAL;
@@ -1279,8 +1278,6 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
         netdev->ethtool_ops = &xennet_ethtool_ops;
         SET_NETDEV_DEV(netdev, &dev->dev);
 
-        netif_set_gso_max_size(netdev, XEN_NETIF_MAX_TX_SIZE - MAX_TCP_HEADER);
-
         np->netdev = netdev;
 
         netif_carrier_off(netdev);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dcf6ec27739b..278738873703 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2185,6 +2185,12 @@ void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
+DECLARE_PER_CPU(int, xmit_recursion);
+static inline int dev_recursion_level(void)
+{
+        return this_cpu_read(xmit_recursion);
+}
+
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
diff --git a/include/net/ip.h b/include/net/ip.h
index 025c61c0dffb..6cc1eafb153a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -453,22 +453,6 @@ static __inline__ void inet_reset_saddr(struct sock *sk)
 
 #endif
 
-static inline int sk_mc_loop(struct sock *sk)
-{
-        if (!sk)
-                return 1;
-        switch (sk->sk_family) {
-        case AF_INET:
-                return inet_sk(sk)->mc_loop;
-#if IS_ENABLED(CONFIG_IPV6)
-        case AF_INET6:
-                return inet6_sk(sk)->mc_loop;
-#endif
-        }
-        WARN_ON(1);
-        return 1;
-}
-
 bool ip_call_ra_chain(struct sk_buff *skb);
 
 /*
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 1d09b46c1e48..eda131d179d9 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -174,7 +174,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));
 
 static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 {
-        struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
+        struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
+                                inet6_sk(skb->sk) : NULL;
 
         return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ?
                skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
diff --git a/include/net/sock.h b/include/net/sock.h
index ab186b1d31ff..e4079c28e6b8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1762,6 +1762,8 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
 
 struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
 
+bool sk_mc_loop(struct sock *sk);
+
 static inline bool sk_can_gso(const struct sock *sk)
 {
         return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
diff --git a/net/core/dev.c b/net/core/dev.c
index 962ee9d71964..45109b70664e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2848,7 +2848,9 @@ static void skb_update_prio(struct sk_buff *skb)
 #define skb_update_prio(skb)
 #endif
 
-static DEFINE_PER_CPU(int, xmit_recursion);
+DEFINE_PER_CPU(int, xmit_recursion);
+EXPORT_SYMBOL(xmit_recursion);
+
 #define RECURSION_LIMIT 10
 
 /**
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 44706e81b2e0..e4fdc9dfb2c7 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -175,9 +175,9 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
 
         spin_lock(&net->rules_mod_lock);
         list_del_rcu(&ops->list);
-        fib_rules_cleanup_ops(ops);
         spin_unlock(&net->rules_mod_lock);
 
+        fib_rules_cleanup_ops(ops);
         call_rcu(&ops->rcu, fib_rules_put_rcu);
 }
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 5221f975a4cc..70d3450588b2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -198,8 +198,10 @@ static int __peernet2id(struct net *net, struct net *peer, bool alloc)
  */
 int peernet2id(struct net *net, struct net *peer)
 {
-        int id = __peernet2id(net, peer, true);
+        bool alloc = atomic_read(&peer->count) == 0 ? false : true;
+        int id;
 
+        id = __peernet2id(net, peer, alloc);
         return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
 }
 EXPORT_SYMBOL(peernet2id);
@@ -349,7 +351,7 @@ static LIST_HEAD(cleanup_list);  /* Must hold cleanup_list_lock to touch */
 static void cleanup_net(struct work_struct *work)
 {
         const struct pernet_operations *ops;
-        struct net *net, *tmp, *peer;
+        struct net *net, *tmp;
         struct list_head net_kill_list;
         LIST_HEAD(net_exit_list);
 
@@ -365,6 +367,14 @@ static void cleanup_net(struct work_struct *work)
         list_for_each_entry(net, &net_kill_list, cleanup_list) {
                 list_del_rcu(&net->list);
                 list_add_tail(&net->exit_list, &net_exit_list);
+                for_each_net(tmp) {
+                        int id = __peernet2id(tmp, net, false);
+
+                        if (id >= 0)
+                                idr_remove(&tmp->netns_ids, id);
+                }
+                idr_destroy(&net->netns_ids);
+
         }
         rtnl_unlock();
 
@@ -390,26 +400,12 @@ static void cleanup_net(struct work_struct *work)
          */
         rcu_barrier();
 
-        rtnl_lock();
         /* Finally it is safe to free my network namespace structure */
         list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
-                /* Unreference net from all peers (no need to loop over
-                 * net_exit_list because idr_destroy() will be called for each
-                 * element of this list.
-                 */
-                for_each_net(peer) {
-                        int id = __peernet2id(peer, net, false);
-
-                        if (id >= 0)
-                                idr_remove(&peer->netns_ids, id);
-                }
-                idr_destroy(&net->netns_ids);
-
                 list_del_init(&net->exit_list);
                 put_user_ns(net->user_ns);
                 net_drop_ns(net);
         }
-        rtnl_unlock();
 }
 static DECLARE_WORK(net_cleanup_work, cleanup_net);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 78e89eb7eb70..71e3e5f1eaa0 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -653,6 +653,25 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
                 sock_reset_flag(sk, bit);
 }
 
+bool sk_mc_loop(struct sock *sk)
+{
+        if (dev_recursion_level())
+                return false;
+        if (!sk)
+                return true;
+        switch (sk->sk_family) {
+        case AF_INET:
+                return inet_sk(sk)->mc_loop;
+#if IS_ENABLED(CONFIG_IPV6)
+        case AF_INET6:
+                return inet6_sk(sk)->mc_loop;
+#endif
+        }
+        WARN_ON(1);
+        return true;
+}
+EXPORT_SYMBOL(sk_mc_loop);
+
 /*
  *      This is meant for all protocols to use and covers goings on
  *      at the socket level. Everything here is generic.
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index faf7cc3483fe..9d66a0f72f90 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -248,7 +248,9 @@ void __init dn_fib_rules_init(void)
 
 void __exit dn_fib_rules_cleanup(void)
 {
+        rtnl_lock();
         fib_rules_unregister(dn_fib_rules_ops);
+        rtnl_unlock();
         rcu_barrier();
 }
 
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 2173402d87e0..4dea2e0681d1 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -501,12 +501,10 @@ static struct net_device *dev_to_net_device(struct device *dev)
 #ifdef CONFIG_OF
 static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
                                         struct dsa_chip_data *cd,
-                                        int chip_index,
+                                        int chip_index, int port_index,
                                         struct device_node *link)
 {
-        int ret;
         const __be32 *reg;
-        int link_port_addr;
         int link_sw_addr;
         struct device_node *parent_sw;
         int len;
@@ -519,6 +517,10 @@ static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
         if (!reg || (len != sizeof(*reg) * 2))
                 return -EINVAL;
 
+        /*
+         * Get the destination switch number from the second field of its 'reg'
+         * property, i.e. for "reg = <0x19 1>" sw_addr is '1'.
+         */
         link_sw_addr = be32_to_cpup(reg + 1);
 
         if (link_sw_addr >= pd->nr_chips)
@@ -535,20 +537,9 @@ static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
                 memset(cd->rtable, -1, pd->nr_chips * sizeof(s8));
         }
 
-        reg = of_get_property(link, "reg", NULL);
-        if (!reg) {
-                ret = -EINVAL;
-                goto out;
-        }
-
-        link_port_addr = be32_to_cpup(reg);
-
-        cd->rtable[link_sw_addr] = link_port_addr;
+        cd->rtable[link_sw_addr] = port_index;
 
         return 0;
-out:
-        kfree(cd->rtable);
-        return ret;
 }
 
 static void dsa_of_free_platform_data(struct dsa_platform_data *pd)
@@ -658,7 +649,7 @@ static int dsa_of_probe(struct platform_device *pdev)
                         if (!strcmp(port_name, "dsa") && link &&
                                         pd->nr_chips > 1) {
                                 ret = dsa_of_setup_routing_table(pd, cd,
-                                                chip_index, link);
+                                                chip_index, port_index, link);
                                 if (ret)
                                         goto out_free_chip;
                         }
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 57be71dd6a9e..23b9b3e86f4c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1111,11 +1111,10 @@ static void ip_fib_net_exit(struct net *net)
 {
         unsigned int i;
 
+        rtnl_lock();
 #ifdef CONFIG_IP_MULTIPLE_TABLES
         fib4_rules_exit(net);
 #endif
-
-        rtnl_lock();
         for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
                 struct fib_table *tb;
                 struct hlist_head *head;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 92825443fad6..fe54eba6d00d 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -278,11 +278,13 @@ static void __net_exit ipmr_rules_exit(struct net *net)
 {
         struct mr_table *mrt, *next;
 
+        rtnl_lock();
         list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) {
                 list_del(&mrt->list);
                 ipmr_free_table(mrt);
         }
         fib_rules_unregister(net->ipv4.mr_rules_ops);
+        rtnl_unlock();
 }
 #else
 #define ipmr_for_each_table(mrt, net) \
@@ -308,7 +310,10 @@ static int __net_init ipmr_rules_init(struct net *net)
 
 static void __net_exit ipmr_rules_exit(struct net *net)
 {
+        rtnl_lock();
         ipmr_free_table(net->ipv4.mrt);
+        net->ipv4.mrt = NULL;
+        rtnl_unlock();
 }
 #endif
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fb4cf8b8e121..f501ac048366 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3105,10 +3105,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
                         if (!first_ackt.v64)
                                 first_ackt = last_ackt;
 
-                        if (!(sacked & TCPCB_SACKED_ACKED))
+                        if (!(sacked & TCPCB_SACKED_ACKED)) {
                                 reord = min(pkts_acked, reord);
-                        if (!after(scb->end_seq, tp->high_seq))
-                                flag |= FLAG_ORIG_SACK_ACKED;
+                                if (!after(scb->end_seq, tp->high_seq))
+                                        flag |= FLAG_ORIG_SACK_ACKED;
+                        }
                 }
 
                 if (sacked & TCPCB_SACKED_ACKED)
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 27ca79682efb..70bc6abc0639 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -322,7 +322,9 @@ out_fib6_rules_ops:
 
 static void __net_exit fib6_rules_net_exit(struct net *net)
 {
+        rtnl_lock();
         fib_rules_unregister(net->ipv6.fib6_rules_ops);
+        rtnl_unlock();
 }
 
 static struct pernet_operations fib6_rules_net_ops = {
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7e80b61b51ff..36cf0ab685a0 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -542,7 +542,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
         struct sk_buff *frag;
         struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
-        struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
+        struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
+                                inet6_sk(skb->sk) : NULL;
         struct ipv6hdr *tmp_hdr;
         struct frag_hdr *fh;
         unsigned int mtu, hlen, left, len;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 52028f449a89..312e0ff47339 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -267,8 +267,8 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
                 list_del(&mrt->list);
                 ip6mr_free_table(mrt);
         }
-        rtnl_unlock();
         fib_rules_unregister(net->ipv6.mr6_rules_ops);
+        rtnl_unlock();
 }
 #else
 #define ip6mr_for_each_table(mrt, net) \
@@ -336,7 +336,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 
 static void ip6mr_free_table(struct mr6_table *mrt)
 {
-        del_timer(&mrt->ipmr_expire_timer);
+        del_timer_sync(&mrt->ipmr_expire_timer);
         mroute_clean_tables(mrt);
         kfree(mrt);
 }
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 895348e44c7d..a29a504492af 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1871,6 +1871,7 @@ static int __init l2tp_init(void)
         l2tp_wq = alloc_workqueue("l2tp", WQ_UNBOUND, 0);
         if (!l2tp_wq) {
                 pr_err("alloc_workqueue failed\n");
+                unregister_pernet_device(&l2tp_net_ops);
                 rc = -ENOMEM;
                 goto out;
         }